CN111404676B - Method and device for generating, storing and transmitting secret key and ciphertext - Google Patents
Method and device for generating, storing and transmitting secret key and ciphertext Download PDFInfo
- Publication number
- CN111404676B CN111404676B CN202010133567.1A CN202010133567A CN111404676B CN 111404676 B CN111404676 B CN 111404676B CN 202010133567 A CN202010133567 A CN 202010133567A CN 111404676 B CN111404676 B CN 111404676B
- Authority
- CN
- China
- Prior art keywords
- ciphertext
- joint model
- key
- generating
- specific target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0816—Key establishment, i.e. cryptographic processes or cryptographic protocols whereby a shared secret becomes available to two or more parties, for subsequent use
- H04L9/0819—Key transport or distribution, i.e. key establishment techniques where one party creates or otherwise obtains a secret value, and securely transfers it to the other(s)
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/06—Network architectures or network communication protocols for network security for supporting key management in a packet data network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0861—Generation of secret information including derivation or calculation of cryptographic keys or passwords
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0894—Escrow, recovery or storing of secret information, e.g. secret key escrow or cryptographic key storage
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Storage Device Security (AREA)
Abstract
The present disclosure provides a method for generating, storing and transmitting a secret key and a ciphertext, which pre-establishes and trains a joint model; when the trained joint model detects a given specific target, a text sentence corresponding to the given specific target is generated through a feature extraction module and a multi-path key generation module in the joint model; encrypting the security information with a key generated by all or part of the text sentence to generate a ciphertext; encapsulating the ciphertext and the joint model in a preset application program; and performing hidden storage and transfer operation on the ciphertext and the joint model which are packaged together. The method is used for dynamically generating the secret key for encrypting and decrypting the security information, and the risk of secret key storage is avoided; and the dynamic key can trigger generation when a specific target appears, so that the generation, storage and transmission of the ciphertext have safety and confidentiality, and the ciphertext can only be decrypted and used by a target user. The disclosure also provides a device for generating, storing and transmitting the secret key and the ciphertext.
Description
Technical Field
The disclosure relates to the technical field of network space security, in particular to a method and a device for generating, storing and transmitting a secret key and a ciphertext.
Background
At present, a computer network is generally used by military units for product design and production management, and the occurrence of secret leakage caused by computers is increased. To ensure the security of national secrets, countries exercise a secret qualification certification regime for units engaged in the scientific research and production of the military and impose strict security requirements on the military or other secret-related units. On the other hand, many scientific research institutions have very precious scientific research materials or result data, researchers want to have complete interpretation rights to the contents before publishing them publicly, and do not want to obtain the contents by external personnel or malicious stealers, so they also want to store and transfer the scientific research results or precious data in a secret manner. Moreover, many communication related to national security and benefit usually uses anonymous communication, but anonymous communication is vulnerable to traffic inspection attack of attacker, so that the anonymous communication also has high requirement on the security of communication content. For convenience, the secret-related files, scientific research data or communication content and the like with the requirements are collectively called security information, and the encrypted security information is collectively called ciphertext.
Based on such a background, many researchers adopt various different encryption technologies to encrypt the security information to form ciphertext and store and transmit the ciphertext, but there is a problem that a large number of different ciphertexts correspond to a large number of keys, and then the keys need to be recorded and stored, however, the current technology cannot guarantee the security of key storage, so that the risk of disclosure exists in the current storage and transmission process of the keys and ciphertexts.
At present, encryption and preservation of the safety information face the risk of losing or being stolen, and once the secret key is lost, a person who only needs to take the secret key can decrypt the ciphertext to obtain the safety information, so that the generation, storage and transmission of the secret key and the ciphertext face safety threat.
Disclosure of Invention
In order to solve the technical problems in the prior art, the embodiment of the disclosure provides a method and a device for generating, storing and transmitting a secure secret key and a ciphertext, wherein the method enables the model to correspond to different specific targets, generates a corresponding stable dynamic encryption and decryption key, and realizes multi-channel information protection; and the dynamically stable encryption and decryption key is at least 128 bits long, so that a malicious attacker cannot finish decryption of the ciphertext even if the malicious attacker obtains the ciphertext, cannot obtain effective information, and improves the safety of information transmission.
In a first aspect, an embodiment of the present disclosure provides a method for generating, storing and transmitting a secure secret key and a ciphertext, including the following steps: pre-building and training a joint model; when the trained joint model detects a given specific target, a text sentence corresponding to the given specific target is generated through a feature extraction module and a multi-path key generation module in the joint model; encrypting the security information by using a key generated by all or part of the text sentence to generate a ciphertext; packaging the ciphertext and the joint model in a preset application program; and carrying out hidden storage and transfer operation on the ciphertext and the joint model which are packaged together.
In one embodiment, the pre-building and training the joint model includes: and combining the convolutional neural network and the recurrent neural network to construct the joint model corresponding to the generation of the multipath keys.
In one embodiment, the method further comprises: training the joint model by taking a plurality of types of feature libraries as a data set; in the trained joint model, the output of the feature extraction module is at least 128 x 1-dimensional high-dimensional features, wherein the feature libraries of the multiple types comprise one or more of an image library, an audio library, a video library, a user behavior library, a software environment library and/or a physical environment library.
In one embodiment, the encryption key of the multiple key generation module is dynamic.
In one embodiment, when the trained joint model detects a given specific target, generating, by the feature extraction module and the multi-path key generation module in the joint model, a text sentence corresponding to the given specific target includes: the feature extraction module performs feature extraction on a given specific target by adopting a convolutional neural network.
In one embodiment, when the trained joint model detects a given specific target, generating, by the feature extraction module and the multi-path key generation module in the joint model, a text sentence corresponding to the given specific target includes: the multi-path key generation module receives the high-dimensional feature data output by the feature extraction module based on a recurrent neural network, and outputs text sentences of key information contained in the high-dimensional feature data to generate sentences with bit length of at least 128 bits, wherein the sentences are used for key generation.
In one embodiment, the recurrent neural network adopts a model structure of LSTM or gLSTM architecture.
In a second aspect, embodiments of the present disclosure provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.
In a third aspect, embodiments of the present disclosure provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method described above when the program is executed.
In a fourth aspect, an embodiment of the present disclosure provides a device for generating, storing and transmitting a secure secret key and a ciphertext, where the device includes: the building and training module is used for pre-building and training a joint model; the first generation module is used for generating a text sentence corresponding to a given specific target through the feature extraction module and the multipath key generation module in the joint model when the trained joint model detects the given specific target; the second generation module is used for encrypting the security information by using the secret key generated by all or part of the text sentences to generate ciphertext; the packaging module is used for packaging the ciphertext and the joint model in a preset application program; and the storage and transmission module is used for carrying out hidden storage and transmission operation on the ciphertext and the joint model which are packaged together.
The application provides a method and a device for generating, storing and transmitting a secret key and a ciphertext, which are used for pre-establishing and training a joint model; when the trained joint model detects a given specific target, a text sentence corresponding to the given specific target is generated through a feature extraction module and a multi-path key generation module in the joint model; encrypting the security information by using a key generated by all or part of the text sentence to generate a ciphertext; packaging the ciphertext and the joint model in a preset application program; and carrying out hidden storage and transfer operation on the ciphertext and the joint model which are packaged together. The method can realize high-concealment generation, storage and transmission of a plurality of ciphertexts, and is different from the prior art in that the key used for encrypting and decrypting the security information is dynamically generated, so that the security risk of key storage does not exist; the method is difficult to reverse due to the fact that the stable and secret correct dynamic secret key can be triggered to be generated only when a specific target appears, the secret characteristic of the secret key enables generation, storage and transmission of the ciphertext to be extremely high in safety and secret, the ciphertext can be guaranteed to be decrypted and used only by a target user, and the method is high in safety and usability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required to be used in the following description of the embodiments are briefly introduced:
FIG. 1 is a flowchart illustrating a method for generating, storing and transmitting a secure secret key and a ciphertext according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating an application of a method for generating, storing and transmitting secure secret keys and ciphertext according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating an application of a method for generating, storing and transmitting secure secret keys and ciphertext according to another embodiment of the present application; and
fig. 4 is a schematic structural diagram of a device for generating, storing and transmitting a secure secret key and a ciphertext according to an embodiment of the application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples.
In the following description, the terms "first," "second," and "first," are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The following description provides various embodiments of the present disclosure that may be substituted or combined between different embodiments, and thus the present application is also to be considered as embracing all possible combinations of the same and/or different embodiments described. Thus, if one embodiment includes feature A, B, C and another embodiment includes feature B, D, then the present application should also be considered to include embodiments that include one or more of all other possible combinations including A, B, C, D, although such an embodiment may not be explicitly recited in the following.
In order to make the objects, technical solutions and advantages of the present application more clear, the following embodiments of a method and apparatus for generating, storing and transmitting secure secret keys and ciphertext according to the present application are further described in detail by way of examples with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Firstly, it should be noted that, the method related to the disclosure firstly builds a joint model based on the convolutional neural network and the recurrent neural network, and then uses the joint model to realize hidden storage and dynamic generation of the secret key, thereby ensuring the security of ciphertext generation, storage and transmission, and decrypting the corresponding ciphertext and releasing the corresponding security information only when the joint model detects a specific target in the ciphertext storage and transmission process. In addition, the method disclosed by the application can realize very high security secret storage and transmission of the security information. Secondly, in order to ensure security concealment, the hidden storage and dynamic concealment generation of the secret key are realized based on an artificial intelligence technology, and then the secret key is used for encrypting the security information to generate a security concealed ciphertext, so that the key information hidden in the ciphertext cannot be decrypted and found, the reverse intention concealment resistance is realized, and the security information protection method can be used for protecting secret information or avoiding flow inspection attacks of attackers.
Fig. 1 is a flow chart of a method for generating, storing and transmitting a secure secret key and a ciphertext according to an embodiment, which specifically includes the following steps:
step 101, a joint model is built and trained in advance.
Specifically, in one embodiment, pre-building and training the joint model includes: and combining the convolutional neural network and the recurrent neural network to construct the joint model corresponding to the generation of the multipath keys. It should be noted that, the convolutional neural network and the recurrent neural network are core components used when the present disclosure is used to construct a joint model, and the present disclosure emphasizes the use of these two types of neural network models, including but not limited to, and can be replaced for a model structure that can implement the core functions of the secret key and ciphertext, the storage and transmission method of the security privacy related to the present disclosure. Further, the model may generate stable dynamic keys for different classes of specific targets for encrypting multiple pieces of security information. The stability referred to herein means that the dynamic encryption keys generated are identical for the same class of specific objects, e.g., all Zhou Xingchi facial images, within an acceptable fault tolerance.
And 102, when the trained joint model detects a given specific target, generating a text sentence corresponding to the given specific target through a feature extraction module and a multi-path key generation module in the joint model. Wherein the encryption key of the multi-path key generation module is dynamic.
Specifically, in one embodiment, the method for generating, storing and transmitting the secure secret key and the ciphertext according to the present disclosure further includes: training the joint model by taking a plurality of types of feature libraries as a data set; in the trained joint model, the output of the feature extraction module is at least 128 x 1-dimensional high-dimensional features, wherein the feature libraries of the multiple types comprise one or more of an image library, an audio library, a video library, a user behavior library, a software environment library and/or a physical environment library.
Further, when the trained joint model detects a given specific target, generating a text sentence corresponding to the given specific target through a feature extraction module and a multi-path key generation module in the joint model includes: the feature extraction module performs feature extraction on a given specific target by adopting a convolutional neural network.
Further, when the trained joint model detects a given specific target, generating a text sentence corresponding to the given specific target through a feature extraction module and a multi-path key generation module in the joint model includes: the multi-path key generation module receives the high-dimensional feature data output by the feature extraction module based on the recurrent neural network, and outputs text sentences of key information contained in the high-dimensional feature data to generate sentences with bit length of at least 128 bits, wherein the sentences are used for key generation. The model structure adopted by the recurrent neural network is an LSTM or gLSTM architecture, and it should be noted that the model structure adopted by the recurrent neural network includes, but is not limited to, the LSTM or gLSTM architecture described above.
And step 103, encrypting the security information with a key defined by all or part of the text sentence to generate ciphertext.
And 104, packaging the ciphertext and the joint model in a preset application program.
And 105, performing hidden storage and transmission operation on the ciphertext and the joint model which are packaged together.
It should be noted that, when the preset application program is started, the joint model encapsulated therein also starts to run, and whether the feature target appears is detected in real time. When the unspecified target appears, the application program is normally executed; when a specific target appears, the application program can trigger the generation of a correct and stable dynamic key while normally executing, so that the corresponding ciphertext is decrypted. The secret of the generation, storage and transmission method of the secret key and the ciphertext related to the present disclosure is related to different performances when the secret key and the ciphertext are packaged in a normal preset application program and have non-specific targets and specific targets.
In addition, it should be noted that, the trained joint model and ciphertext are built into a normal application program, and do not affect the normal function of the application program. In subsequent decryption operations, this trained joint model is the store, generator, and passer of the dynamic decryption key. Therefore, the method can realize that the built-in joint model in the application program can generate stable and correct dynamic decryption keys corresponding to different specific targets if and only if the specific targets appear, the dynamic decryption keys are used for decrypting corresponding ciphertext to release corresponding safety information, and the secret storage and transmission of other keys and ciphertext can be guaranteed not to be affected.
In order to more clearly and accurately understand and apply the method for generating, storing and transmitting the secure secret key and the ciphertext related to the present disclosure, the following examples are performed. It should be noted that the scope of protection of the present disclosure is not limited to the following examples.
With reference to fig. 2, because many military industry or other confidential units currently have high demands for confidential and secret storage of confidential documents, and many pieces of precious scientific research data or other security information with high demands on completeness currently need to be continuously encrypted and stored in a hidden manner. In addition, many secret or secret related communications are often attacked by traffic inspection by malicious attackers, and in order to protect these security information that needs to be stored in a secret manner, a novel method for generating, storing and transmitting ciphertext is required, and it is ensured that the corresponding secret key cannot be easily stolen. Therefore, the method related to the disclosure is based on artificial intelligence technology, and provides a method for generating, storing and transmitting secret keys and ciphertext, the overall architecture of which is shown in fig. 2. The overall architecture consists of two parts, namely multi-path encryption and unique decryption.
It should be noted that the joint model is a core component in the method related to the disclosure, and is a neural network model that is trained based on a feature library established by us. The feature library of the present disclosure may be an image library, an audio library, a video library, a user behavior library, a software environment library, a physical environment library, or the like, and any feature library that can be processed by the feature extraction module in the joint model to obtain stable high-dimensional (at least 128×1) features may be used as a data set trained by the joint model. These feature libraries are used as inputs to the joint model for training the joint model so that the trained joint model has higher stability when used as a generator, storage and transmitter of dynamic stabilization keys. Preferably, we will describe in detail the method to which the present disclosure relates, taking image recognition as an example.
Referring to fig. 3, taking a trained joint model for image recognition as an example, when multiple ciphertexts need to be generated, stored and transferred in a secret manner, multiple paths of ciphertexts need to be encrypted, and multiple paths of security information are encrypted to generate multiple paths of ciphertexts by using a dynamic encryption key generated by the joint model. Each ciphertext generated corresponds to a particular target of a different class, but often there is more than one identifiable object in the particular target to which each ciphertext corresponds.
Taking ciphertext i as an example, the multi-path encryption process may be categorized into the following steps. Specifically, given a specific target, i.e. assuming that the specific target of the ciphertext i is a type of picture corresponding to a text sentence as shown in fig. 3 as "Three dogs play in the grass", at least some characteristics such as a lawn, 3 dogs, and an action representing play need to be contained in such a picture.
A dynamically stable key is one premise of ciphertext generation. When the trained joint model detects a given specific target, a feature extraction module and a multi-path key generation module are used for generating a text sentence corresponding to the given specific target, namely 'Three dogs play in the grass', the title can be directly used as an encryption key, or the complexity of a generated dynamic key is further improved through a certain operation, but the uniqueness and the stability of the encryption key corresponding to the given specific target can be guaranteed, and the length of the generated key can be guaranteed to be at least 128 bits.
The feature extraction module adopts a convolutional neural network to perform feature extraction on a given specific target. The convolutional neural network comprehensively considers the shape and the spatial information of the image, can effectively capture and extract the image characteristics, and uses the characteristics of the final full-connection layer or the convolutional layer of the network as the characteristics of the image. In this module, the feature output by us is guaranteed to be high-dimensional (at least 128×1) data, for example, after the processing of the module in fig. 3, the corresponding output high-dimensional feature data contains key information of "dog", "play" and "grass".
The multi-path key generation module is realized based on a recurrent neural network, receives the high-dimensional characteristic data output by the characteristic extraction module, outputs text sentences from key information contained in the high-dimensional characteristic data, generates sentences with fluency and readability, and ensures that the bit length of the generated sentences is at least 128 bits. With a guaranteed key length of at least 128, the present application directly uses bit ordering of all or part of the sentence text sentence as encryption key. It is within the recognition scope of the present application that the sentence text sentence is converted into an encryption or decryption key without being limited to the direct use of bits, and that the complexity of the key be enhanced by some operation. In addition, the recurrent neural network can adopt various architectures such as LSTM, gLSTM and the like, and can be added with an attention mechanism and the like, so long as the objective task of the application can be completed.
It should be noted that, in this embodiment, only a simple example is given by using a ciphertext i, which is a key generation on a single path. The principle of corresponding multipath is the same, the combined model trains specific targets of different types in the training process, when m ciphertext needs to be generated, stored and transmitted, the types of the specific targets to be trained in the combined model training process are at least (m+1), and under the condition that an attacker cannot obtain a training data set even if the trained model is obtained, the pictures tried to be input do not belong to the specific target types corresponding to the m ciphertext.
The present disclosure encrypts security information i with a generated key (key-i) to generate ciphertext i. If m pieces of security information exist, m pieces of ciphertext are correspondingly generated through the generated m pieces of dynamic encryption keys respectively. All the generated ciphertext together with the joint model is encapsulated in a normal application (EXE), and the normal function of the encapsulated application is not affected. The key and ciphertext for decryption are stored and transferred in a hidden manner in the packaged EXE, their hidden generation only taking place in the presence of a specific object.
Further, it should be noted that, while an application program having a ciphertext and a joint model built therein starts running, the built-in joint model will also start, and it will detect whether there is an input that the current model can process. When such an input is present, the joint model will do feature extraction for the input and the multi-way key generation module will attempt to convert the generated high-dimensional feature data into text sentence sentences, thereby generating possible keys to attempt to decrypt all ciphertext. When the input is a non-specific target, the generated possible secret key is wrong, and the ciphertext cannot be decrypted to obtain the safety information; if and only if the input is a specific target, the generated possible key is correct, and the occurrence of a specific target can only give a corresponding key through the joint model, so that the corresponding ciphertext can be decrypted, a piece of corresponding safety information is obtained, and the method is not applicable to other ciphertexts, so that the safety information in other ciphertexts is not exposed.
It can be understood that the overall architecture comprises two modules of multi-path encryption and uniqueness decryption, wherein the core component is a joint model realized based on a convolutional neural network and a recurrent neural network, and the joint model is a method for generating, storing and transmitting a secure secret key and a ciphertext based on an artificial intelligence technology. The independence between the secret keys and the ciphertext on different encryption and decryption links is guaranteed through multipath encryption and uniqueness decryption, the corresponding ciphertext is triggered to be decrypted only when the corresponding specific target appears, safety information is released, and the secret storage and transmission of other ciphertexts can be guaranteed not to be affected.
In summary, based on the requirements of military industry or secret-related units, scientific research units, anonymous communication and the like for generating, storing and transmitting secret keys and ciphertext in a safe and secret-related manner, the method for generating, storing and transmitting the secret keys and the ciphertext has the technical characteristics that encryption and decryption secret keys are dynamically generated, and compared with the existing pure encryption technology, the method does not need to store secret keys, and the secret keys for encryption and decryption are dynamically generated, so that malicious operations such as theft of secret keys by malicious stealers or attackers are prevented; secondly, the method related to the present disclosure can realize the secret storage and transmission of a plurality of secret keys and ciphertext at the same time, and compared with the existing secret transmission method of single information, the method related to the present disclosure is more efficient, and a great amount of model training time is saved; further, the secret security achieved by the method is extremely high, even if a security analysis expert is difficult to achieve reverse, even if a trained open source model and ciphertext are obtained, a malicious attacker can hardly obtain a dynamic decryption key, and therefore cannot obtain the decryption ciphertext to obtain security information. This is because malicious attackers can only crack the output data of the model through massive attempts without knowing the training data set, especially if a particular target contains multiple features, brute force cracking is almost impossible in a limited time.
The application provides a method for generating, storing and transmitting a secret key and a ciphertext, which is used for pre-establishing and training a joint model; when the trained joint model detects a given specific target, a text sentence corresponding to the given specific target is generated through a feature extraction module and a multi-path key generation module in the joint model; and encrypting the security information by using a key defined by all or part of the text sentence to generate a ciphertext, and carrying out hidden storage and transmission operation on the ciphertext and the joint model which are packaged together. The method can realize high-concealment generation, storage and transmission of a plurality of ciphertexts, and is different from the prior art in that the key used for encrypting and decrypting the security information is dynamically generated, so that the security risk of key storage does not exist; the method is difficult to reverse due to the fact that the stable and secret correct dynamic secret key can be triggered to be generated only when a specific target appears, the secret characteristic of the secret key enables generation, storage and transmission of the ciphertext to be extremely high in safety and secret, the ciphertext can be guaranteed to be decrypted and used only by a target user, and the method is high in safety and usability.
Based on the same inventive concept, a device for generating, storing and transmitting the secret key and the ciphertext is also provided. Because the principle of the device for solving the problem is similar to the method for generating, storing and transmitting the secure secret key and the ciphertext, the implementation of the device can be realized according to the specific steps of the method, and the repetition is omitted.
Fig. 4 is a schematic structural diagram of a device for generating, storing and transmitting a secure secret key and a ciphertext according to an embodiment. The secure secret key and ciphertext generating, storing and transmitting device 10 includes: the system comprises a building and training module 100, a first generating view 200, a second generating module 300, a packaging module 400 and a storage and transfer module 500.
Wherein, the building and training module 100 is used for pre-building and training a joint model; the first generating module 200 is configured to generate a text sentence corresponding to a given specific target through the feature extracting module and the multi-path key generating module in the joint model when the trained joint model detects the given specific target; the second generation module 300 is configured to encrypt the security information with a key generated by all or part of the text sentence to generate a ciphertext; the packaging module 400 is configured to package the ciphertext and the joint model in a preset application program; the storage and delivery module 500 is configured to perform hidden storage and delivery operations on the ciphertext and the federation model that are packaged together.
The application provides a generation, storage and transmission device of a safe secret key and a ciphertext, which comprises the following steps of firstly, pre-establishing and training a joint model through a building and training module; when the given specific target is detected through the joint model trained by the first generation module, generating a text sentence corresponding to the given specific target through a feature extraction module and a multi-path key generation module in the joint model; encrypting the security information by using a key generated by all or part of the text sentences through a second generation module to generate ciphertext; packaging the ciphertext and the joint model in a preset application program through a packaging module; and finally, carrying out hidden storage and transmission operation on the ciphertext and the joint model which are packaged together through a storage and transmission module. The device can realize high-concealment generation, storage and transmission of a plurality of ciphertexts, and is different from the prior art in that the key for encrypting and decrypting the safety information is dynamically generated, so that the safety risk of key storage does not exist; the device related to the present disclosure is difficult to be reversed due to the characteristic that the stable and secret correct dynamic key can be triggered to be generated only when a specific target appears, the secret characteristic of the key enables the generation, storage and transmission of the ciphertext to have extremely high safety and confidentiality, the ciphertext can be ensured to be decrypted and used only by a target user, and the device has higher safety and usability.
Embodiments of the present application also provide a computer-readable storage medium having a computer program stored thereon, the program being executed by the processor of fig. 1.
Embodiments of the present application also provide a computer program product comprising instructions. The computer program product, when run on a computer, causes the computer to perform the method of fig. 1 described above.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
The basic principles of the present disclosure have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present disclosure. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, since the disclosure is not necessarily limited to practice with the specific details described.
The block diagrams of the devices, apparatuses, devices, systems referred to in this disclosure are merely illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
In addition, as used herein, the use of "or" in the recitation of items beginning with "at least one" indicates a separate recitation, e.g., "at least one of A, B or C" recitation means a or B or C, or AB or AC or BC, or ABC (i.e., a and B and C). Furthermore, the term "exemplary" does not mean that the described example is preferred or better than other examples.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the disclosure to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (7)
1. The method for generating, storing and transmitting the secret key and the ciphertext is characterized by comprising the following steps:
pre-building and training a joint model;
when the trained joint model detects a given specific target, a text sentence corresponding to the given specific target is generated through a feature extraction module and a multi-path key generation module in the joint model;
encrypting the security information by using a key generated by all or part of the text sentence to generate a ciphertext;
packaging the ciphertext and the joint model in a preset application program;
performing hidden storage and transfer operation on the ciphertext and the joint model which are packaged together;
when the trained joint model detects a given specific target, generating a text sentence corresponding to the given specific target through a feature extraction module and a multi-path key generation module in the joint model comprises the following steps: the feature extraction module adopts a convolutional neural network to perform feature extraction on a given specific target;
when the trained joint model detects a given specific target, generating a text sentence corresponding to the given specific target through a feature extraction module and a multi-path key generation module in the joint model comprises the following steps: the multi-path key generation module receives the high-dimensional feature data output by the feature extraction module based on a recurrent neural network, and outputs text sentences of key information contained in the high-dimensional feature data to generate sentences with bit length of at least 128 bits, wherein the sentences are used for key generation.
2. The method for generating, storing and transmitting the secure secret key and ciphertext according to claim 1, wherein the pre-building and training the joint model comprises: and combining the convolutional neural network and the recurrent neural network to construct the joint model corresponding to the generation of the multipath keys.
3. The method for generating, storing and transmitting the secure secret key and the ciphertext according to claim 1, further comprising: training the joint model by taking a plurality of types of feature libraries as a data set;
in the trained joint model, the output of the feature extraction module is at least 128 x 1-dimensional high-dimensional features, wherein the feature libraries of the multiple types comprise one or more of an image library, an audio library, a video library, a user behavior library, a software environment library and/or a physical environment library.
4. The method for generating, storing and transmitting the secure secret key and the ciphertext according to claim 1, wherein the encryption key of the multi-path key generation module is dynamic.
5. The method for generating, storing and transmitting the secure secret key and the ciphertext according to claim 1, wherein the recurrent neural network adopts a model structure of LSTM or gLSTM architecture.
6. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any of the claims 1-5.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1-5 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010133567.1A CN111404676B (en) | 2020-03-02 | 2020-03-02 | Method and device for generating, storing and transmitting secret key and ciphertext |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010133567.1A CN111404676B (en) | 2020-03-02 | 2020-03-02 | Method and device for generating, storing and transmitting secret key and ciphertext |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111404676A CN111404676A (en) | 2020-07-10 |
| CN111404676B true CN111404676B (en) | 2023-08-29 |
Family
ID=71432158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010133567.1A Active CN111404676B (en) | 2020-03-02 | 2020-03-02 | Method and device for generating, storing and transmitting secret key and ciphertext |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111404676B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516723A (en) * | 2020-11-19 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Face picture encryption method and device, computer equipment and storage medium |
| CN113079004B (en) * | 2021-03-26 | 2022-11-15 | 北京丁牛科技有限公司 | Multi-user-oriented information transmission method and device |
| CN113190806A (en) * | 2021-04-25 | 2021-07-30 | 北京丁牛科技有限公司 | Data processing method |
| CN116563875B (en) * | 2023-07-05 | 2023-09-08 | 四川集鲜数智供应链科技有限公司 | Intelligent image-text recognition method and system with encryption function |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279495A (en) * | 2015-10-23 | 2016-01-27 | 天津大学 | Video description method based on deep learning and text summarization |
| CN109711464A (en) * | 2018-12-25 | 2019-05-03 | 中山大学 | Image Description Methods based on the building of stratification Attributed Relational Graps |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102587254B1 (en) * | 2016-10-31 | 2023-10-13 | 한국전자통신연구원 | Method and apparatus for key generation based on face recognition using cnn and rnn |
-
2020
- 2020-03-02 CN CN202010133567.1A patent/CN111404676B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279495A (en) * | 2015-10-23 | 2016-01-27 | 天津大学 | Video description method based on deep learning and text summarization |
| CN109711464A (en) * | 2018-12-25 | 2019-05-03 | 中山大学 | Image Description Methods based on the building of stratification Attributed Relational Graps |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111404676A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111404676B (en) | Method and device for generating, storing and transmitting secret key and ciphertext | |
| EP3035585B1 (en) | S-box selection in white-box cryptographic implementation | |
| US10686764B2 (en) | Executable coded cipher keys | |
| Sharma et al. | Guess: genetic uses in video encryption with secret sharing | |
| Millen et al. | Protocol-independent secrecy | |
| Yahaya et al. | Cryptosystem for secure data transmission using Advance Encryption Standard (AES) and Steganography | |
| Santoso et al. | Implementation of AES cryptography and twofish hybrid algorithms for cloud | |
| Pavani et al. | Data Security and Privacy Issues in Cloud Environment | |
| Barukab et al. | Secure communication using symmetric and asymmetric cryptographic techniques | |
| Blaze | Key escrow from a safe distance: looking back at the clipper chip | |
| Neforawati et al. | Message Digest 5 (MD-5) Decryption Application using Python-Based Dictionary Attack Technique | |
| Singh et al. | The A review of different approaches for improving network security in cryptography | |
| Patil et al. | Significant study of data encryption and steganography | |
| Wang et al. | BSVMS: novel autonomous trustworthy scheme for video monitoring | |
| Mathur et al. | The Evolution and Impact of Cryptography in Ensuring Data Privacy | |
| Sadkhan et al. | Crypto Warfare Techniques-Status, Challenges, and Future Trends | |
| Mohamed | Steganography for better data integrity and privacy | |
| Kabir et al. | Color image encryption for secure transfer over internet: a survey | |
| Wiik | Cybersecurity and cryptographic methods in unmanned systems-a study of the current state in unmanned aerial vehicles and similar systems | |
| Rao et al. | Securing Image using Triple Data Encryption Standard | |
| Bhavitha et al. | Performance Evaluation of AES, DES, RSA, and Paillier Homomorphic for Image Security | |
| Sathya et al. | Secure data storage in cloud system using modern cryptography | |
| Nielson | Core Cryptography Technology | |
| Fawzia et al. | Report on Contemporary Cyber Security Issues | |
| Singh | A Review Paper on Network Security and Cryptography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |