CN109995520A - Cipher key transmission methods, image processing platform based on depth convolutional neural networks - Google Patents
Cipher key transmission methods, image processing platform based on depth convolutional neural networks Download PDFInfo
- Publication number
- CN109995520A CN109995520A CN201910167432.4A CN201910167432A CN109995520A CN 109995520 A CN109995520 A CN 109995520A CN 201910167432 A CN201910167432 A CN 201910167432A CN 109995520 A CN109995520 A CN 109995520A
- Authority
- CN
- China
- Prior art keywords
- picture
- convolutional neural
- recipient
- model
- neural networks
- 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.)
- Pending
Links
Classifications
-
- 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
- H04L63/0442—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 wherein the sending and receiving network entities apply asymmetric encryption, i.e. different keys for encryption and decryption
-
- 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)
-
- 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
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)
- Facsimile Transmission Control (AREA)
Abstract
The invention belongs to image procossing, deep learning and field of information security technology, a kind of cipher key transmission methods based on depth convolutional neural networks, image processing platform are disclosed, comprising: choose the picture P as key;Construct depth convolutional neural networks model M;Sender carries out feature extraction to picture P using model M, is used for encryption data for its feature as key K;Picture P is sent to recipient by sender;Recipient uses network model M, carries out feature extraction to picture P and obtains key K for ciphertext data.The present invention use based on scheme, realize the safeguard protection to cipher key delivery in symmetric encipherment algorithm, improve safety and the privacy of encryption information.
Description
Technical field
The invention belongs to image procossing, deep learning and field of information security technology, more particularly to a kind of depth that is based on to roll up
The cipher key transmission methods of product neural network, image processing platform.
Background technique
Currently, the prior art commonly used in the trade is such that the maturation with Internet technology and is widely used, number of users
It ceaselessly transmits and interacts according on network, but these data contain a large amount of privacy and important information, in order to user's
Privacy and property safety, it is necessary to important information be encrypted using Encryption Algorithm.And for the symmetric cryptography in Encryption Algorithm,
Such as AES, the safe transmission of key are also a critically important problem.If key is obtained by attacker, encryption letter
Breath is easy to be stolen by attacker.And in existing solution, asymmetric encryption is usually used, key is encrypted again
It is transmitted, such as rsa encryption, the difficulty that the safety of RSA is decomposed based on big number, public key and private key are that (100 arrive a pair of of Big prime
200 decimal numbers are bigger) function.The difficulty that plaintext is recovered from a public key and ciphertext is equivalent to decompose two big
The product of prime number, this is generally acknowledged difficult math question, however, to ensure that its safety, the key length of RSA cryptographic algorithms is too big, is made
It is higher to obtain operation cost, time-consuming more long, the resource of consumption is more, the scene that unsuitable data take place frequently.
In conclusion problem of the existing technology is: existing encrypted using asymmetric encryption to key is carried out again
Transmission takes a long time, and the resource of consumption is more, the scene that unsuitable data take place frequently.
Solve above-mentioned technical problem difficulty: now in technical solution, be all in efficiency and safety selection sacrifice effect
Rate and improve safety, find that a kind of operation is very fast and the Encryption Algorithm that can not crack has great difficulty.
It solves the meaning of above-mentioned technical problem: while guaranteeing cryptographic security, accelerating encryption times, release more
Resource, safety and development to internet provide bigger guarantee.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of cipher key deliveries based on depth convolutional neural networks
Method, image processing platform.
The invention is realized in this way a kind of cipher key transmission methods based on depth convolutional neural networks, described based on deep
The cipher key transmission methods of degree convolutional neural networks include: the picture P chosen as key;Construct depth convolutional neural networks model
M;Sender carries out feature extraction to picture P using model M, is used for encryption data for its feature as key K;Sender will scheme
Piece P is sent to recipient;Recipient uses network model M, carries out feature extraction to picture P and obtains key K for ciphertext data.
The cipher key transmission methods based on depth convolutional neural networks specifically include:
Step 1, sender choose cipher key carrier picture P, input in depth convolutional neural networks model M.Wherein, depth
Convolutional neural networks model is constructed according to input picture P and generation cipher key size;
Step 2, sender carry out feature extraction to picture P using depth convolutional neural networks model M, obtain key K;
Picture P will be transferred to recipient on line by step 3, sender;
Network model M is transferred to recipient by step 4, sender;
Wherein, if the actual range of sender and recipient are closer, by carrying out mode M under line;If
The actual range of sender and recipient are distant, then asymmetric encryption mode M can be used;
Step 5, recipient will be in the cipher key carrier picture P input model M that received.
Step 6, recipient carry out feature extraction to the picture P received using model M, obtain key K.
Another object of the present invention is to provide the cipher key delivery sides based on depth convolutional neural networks described in a kind of application
The image processing platform of method.
In conclusion advantages of the present invention and good effect are as follows: the present invention solves the safety of symmetric encipherment algorithm key
Transmission problem.Its positive effect considers two kinds of situations: one is sender and recipient's actual range are closer;Such as it is same
Among company or mechanism, the transmission network model M by the way of transmitting (such as USB flash disk) under line, in the net of sender and recipient
Network model M depth can be 1MB by size in the case where only needing in the case where 20 layers zero point several seconds, having a size of 1024 ×
The picture P of 768 pixels extracts the key K that length is 140 bytes;And for identical data, existing asymmetric encryption is calculated
Method, if rsa encryption takes around 5 seconds, but RSA decryption but needs 4 minutes, and efficiency of the invention is obviously relatively high.Other one
Kind of situation is to send hair and recipient apart from distant, can be first using non-right under line in the unpractical situation of transmission network model M
Encryption Algorithm is claimed to transmit network model M;Then it reuses method provided by the present invention and carries out cipher key delivery, in data
In the case where taking place frequently, method efficiency provided by the present invention is still far superior to asymmetric encryption.
Detailed description of the invention
Fig. 1 is the cipher key transmission methods flow chart provided in an embodiment of the present invention based on depth convolutional neural networks.
Fig. 2 is the cipher key transmission methods implementation flow chart provided in an embodiment of the present invention based on depth convolutional neural networks.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, the cipher key transmission methods provided in an embodiment of the present invention based on depth convolutional neural networks include with
Lower step:
S101: the picture P as key is chosen;
S102: building depth convolutional neural networks model M;
S103: sender carries out feature extraction to picture P using model M;
S104: encryption data is used for using its feature as key K;
S105: picture P is sent to recipient by sender;
S106: recipient uses network model M, carries out feature extraction to picture P and obtains key K for ciphertext data.
Application principle of the invention is further described with reference to the accompanying drawing.
As shown in Fig. 2, the cipher key transmission methods provided in an embodiment of the present invention based on depth convolutional neural networks include with
Lower step:
Step 1, sender choose cipher key carrier picture P, input in depth convolutional neural networks model M.
Wherein, depth convolutional neural networks model is constructed according to input picture P and generation cipher key size, in this example
In, input dimension of picture is 1024 × 768 pixels, size 1MB, a total of 20 convolution of depth convolutional neural networks model
Layer.
Step 2, sender carries out feature extraction to picture P using model M, so that key K is obtained, it is in this example, close
140 byte of length of key K.
Picture P will be transferred to recipient on line by step 3, sender.
Network model M is transferred to recipient by step 4, sender.
Wherein, it if the actual range of sender and recipient are closer, can be transmitted by (such as USB flash disk) under line
Model M;If the actual range of sender and recipient are distant, asymmetric encryption mode M can be used.
Step 5, recipient will be in the cipher key carrier picture P input model M that received.
Step 6, recipient carry out feature extraction to the picture P received using model M, obtain key K.
Prove that (specific embodiment/experiment/emulation/Pharmacological Analysis/is able to demonstrate that the front of the invention is real for part
Test data, evidence material, probation report, business data, research and development evidence, business associate evidence etc.)
Two kinds of situations are considered in this example: one is sender and recipient's actual range are closer;Such as the same public affairs
Among department or mechanism, the transmission network model M by the way of transmitting (such as USB flash disk) under line, in the network of sender and recipient
Model M depth can be 1MB by size in the case where only needing in the case where 20 layers zero point several seconds, having a size of 1024 × 768
The picture P of pixel extracts the key K that length is 140 bytes;And for identical data, existing rivest, shamir, adelman,
Such as RSA, under identical machine conditions, encryption is taken around 5 seconds, but RSA decryption but needs 4 minutes, the efficiency of this example
It is obvious relatively high.Another situation is to send hair and recipient apart from distant, the unpractical feelings of transmission network model M under line
Under condition, first network model M can be transmitted using rivest, shamir, adelman;Then the method for reusing this example carries out key
Transmission, in the case where data take place frequently very big with single data volume, it is assumed that need to encrypt the data that n size is 1M, adopt completely
With rsa encryption, n × (5s+4min) is needed, (wherein 5s is the rsa encryption time, and 4min is RSA decryption time);But identical
Under experiment condition, the method for this example only needs 5s+4min+n × 2 × 0.3s, and (wherein 5s is the rsa encryption time, and 4min is
RSA decryption time, 0.3s be in this example network model M extract key time) its efficiency still be far superior to RSA it is asymmetric plus
It is close.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (3)
1. a kind of cipher key transmission methods based on depth convolutional neural networks, which is characterized in that described to be based on depth convolutional Neural
The cipher key transmission methods of network include: the picture P chosen as key;Construct depth convolutional neural networks model M;Sender makes
Feature extraction is carried out to picture P with model M, is used for encryption data for its feature as key K;Picture P is sent to by sender
Recipient;Recipient uses network model M, carries out feature extraction to picture P and obtains key K for ciphertext data.
2. the cipher key transmission methods as described in claim 1 based on depth convolutional neural networks, which is characterized in that described to be based on
The cipher key transmission methods of depth convolutional neural networks specifically include:
Step 1, sender choose cipher key carrier picture P, input in depth convolutional neural networks model M;Wherein, depth convolution
Neural network model is constructed according to input picture P and generation cipher key size;
Step 2, sender carry out feature extraction to picture P using model M, obtain key K;
Picture P will be transferred to recipient on line by step 3, sender;
Network model M is transferred to recipient by step 4, sender;
Wherein, if the actual range of sender and recipient are closer, by carrying out mode M under line;If sent
The actual range of side and recipient are distant, then can be used and non-pile encrypted transmission model M;
Step 5, recipient will be in the cipher key carrier picture P input model M that received.
Step 6, recipient carry out feature extraction to the picture P received using model M, obtain key K.
3. a kind of figure using the cipher key transmission methods based on depth convolutional neural networks described in claim 1~2 any one
As processing platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910167432.4A CN109995520A (en) | 2019-03-06 | 2019-03-06 | Cipher key transmission methods, image processing platform based on depth convolutional neural networks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910167432.4A CN109995520A (en) | 2019-03-06 | 2019-03-06 | Cipher key transmission methods, image processing platform based on depth convolutional neural networks |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109995520A true CN109995520A (en) | 2019-07-09 |
Family
ID=67130058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910167432.4A Pending CN109995520A (en) | 2019-03-06 | 2019-03-06 | Cipher key transmission methods, image processing platform based on depth convolutional neural networks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109995520A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110401536A (en) * | 2019-08-19 | 2019-11-01 | 东南大学 | A kind of common crypto algorithm based on deep learning |
CN111131270A (en) * | 2019-12-27 | 2020-05-08 | 五八有限公司 | Data encryption and decryption method and device, electronic equipment and storage medium |
CN111382455A (en) * | 2020-03-18 | 2020-07-07 | 北京丁牛科技有限公司 | File protection method and device |
CN111723395A (en) * | 2020-05-11 | 2020-09-29 | 华南理工大学 | Portrait biological characteristic privacy protection and decryption method |
CN113179156A (en) * | 2021-03-31 | 2021-07-27 | 杭州电子科技大学 | Handwritten signature biological key generation method based on deep learning |
CN113673676A (en) * | 2021-08-18 | 2021-11-19 | 安谋科技(中国)有限公司 | Electronic device, method for implementing neural network model, system on chip, and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104052658A (en) * | 2014-07-05 | 2014-09-17 | 中国科学技术大学 | Privacy protection system and method based on social network |
CN107330395A (en) * | 2017-06-27 | 2017-11-07 | 中国矿业大学 | A kind of iris image encryption method based on convolutional neural networks |
CN108717680A (en) * | 2018-03-22 | 2018-10-30 | 北京交通大学 | Spatial domain picture steganalysis method based on complete dense connection network |
CN108961137A (en) * | 2018-07-12 | 2018-12-07 | 中山大学 | A kind of image latent writing analysis method and system based on convolutional neural networks |
CN109347633A (en) * | 2018-10-29 | 2019-02-15 | 华南农业大学 | Fuzzy keys communication system and confrontation network system based on deep learning |
-
2019
- 2019-03-06 CN CN201910167432.4A patent/CN109995520A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104052658A (en) * | 2014-07-05 | 2014-09-17 | 中国科学技术大学 | Privacy protection system and method based on social network |
CN107330395A (en) * | 2017-06-27 | 2017-11-07 | 中国矿业大学 | A kind of iris image encryption method based on convolutional neural networks |
CN108717680A (en) * | 2018-03-22 | 2018-10-30 | 北京交通大学 | Spatial domain picture steganalysis method based on complete dense connection network |
CN108961137A (en) * | 2018-07-12 | 2018-12-07 | 中山大学 | A kind of image latent writing analysis method and system based on convolutional neural networks |
CN109347633A (en) * | 2018-10-29 | 2019-02-15 | 华南农业大学 | Fuzzy keys communication system and confrontation network system based on deep learning |
Non-Patent Citations (5)
Title |
---|
吴强: ""CBIR中特征提取技术的比较研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
张庆: ""基于深度学习的虹膜图像加密与活体检测算法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
朱珠: "《物联网异构物品解析与信息发现的研究与设计》", 《中国优秀博硕士学位论文全文数据库信息科技辑》 * |
萝莉: "《基于Chebyshev神经网络加密算法的研究》", 《科技信息》 * |
陈俐君: ""基于深度学习的虹膜图像加密研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110401536A (en) * | 2019-08-19 | 2019-11-01 | 东南大学 | A kind of common crypto algorithm based on deep learning |
CN110401536B (en) * | 2019-08-19 | 2022-09-09 | 东南大学 | General encryption algorithm based on deep learning |
CN111131270A (en) * | 2019-12-27 | 2020-05-08 | 五八有限公司 | Data encryption and decryption method and device, electronic equipment and storage medium |
CN111131270B (en) * | 2019-12-27 | 2021-11-16 | 五八有限公司 | Data encryption and decryption method and device, electronic equipment and storage medium |
CN111382455A (en) * | 2020-03-18 | 2020-07-07 | 北京丁牛科技有限公司 | File protection method and device |
CN111723395A (en) * | 2020-05-11 | 2020-09-29 | 华南理工大学 | Portrait biological characteristic privacy protection and decryption method |
CN111723395B (en) * | 2020-05-11 | 2022-11-18 | 华南理工大学 | Portrait biological characteristic privacy protection and decryption method |
CN113179156A (en) * | 2021-03-31 | 2021-07-27 | 杭州电子科技大学 | Handwritten signature biological key generation method based on deep learning |
CN113179156B (en) * | 2021-03-31 | 2022-05-17 | 杭州电子科技大学 | Handwritten signature biological key generation method based on deep learning |
CN113673676A (en) * | 2021-08-18 | 2021-11-19 | 安谋科技(中国)有限公司 | Electronic device, method for implementing neural network model, system on chip, and medium |
CN113673676B (en) * | 2021-08-18 | 2023-08-18 | 安谋科技(中国)有限公司 | Electronic equipment and implementation method of neural network model, system-on-chip and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109995520A (en) | Cipher key transmission methods, image processing platform based on depth convolutional neural networks | |
US9172529B2 (en) | Hybrid encryption schemes | |
CN107453868B (en) | A kind of safe and efficient quantum key method of servicing | |
CN104219051B (en) | The communication means and system of a kind of inner group message | |
CN105743646B (en) | A kind of Identity based encryption method and system | |
CN110505050A (en) | A kind of Android information encryption system and method based on national secret algorithm | |
CN107342977A (en) | Suitable for the information security method of point-to-point instant messaging | |
CN101188496A (en) | A SMS encryption transport method | |
CN103986583A (en) | Dynamic encryption method and encryption communication system thereof | |
Peng | Danger of using fully homomorphic encryption: A look at Microsoft SEAL | |
CN102523093A (en) | Encapsulation method and encapsulation system for certificate-based key with label | |
CN105323070A (en) | Method for realizing security electronic mail based on digital envelope | |
CN110011995A (en) | Encryption and decryption approaches and device in multi-casting communication | |
CN107181584B (en) | Asymmetric completely homomorphic encryption and key replacement and ciphertext delivery method thereof | |
Acharya et al. | Analysis of cryptographic algorithms for network security | |
CN104092551B (en) | Safe secret key transmission method based on RSA algorithm | |
CN108400862A (en) | A kind of intelligent power trusted end-user data fusion encryption method | |
CN103973713A (en) | Transfer method, extraction method and processing system for electronic mail information | |
Gabriel et al. | Post-quantum crystography: a combination of post-quantum cryptography and steganography | |
CN109831305B (en) | Anti-quantum computation signcryption method and system based on asymmetric key pool | |
CN103004177B (en) | Data transmission security is improved | |
Wanda et al. | Efficient message security based Hyper Elliptic Curve Cryptosystem (HECC) for mobile instant messenger | |
Erondu et al. | An encryption and decryption model for data security using vigenere with advanced encryption standard | |
Gaur et al. | A comparative study and analysis of cryptographic algorithms: RSA, DES, AES, BLOWFISH, 3-DES, and TWOFISH | |
Nagesh et al. | Comparative analysis of MOD-ECDH algorithm with various algorithms |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190709 |