CN114827902A - Identity authentication method and system based on movement track - Google Patents
Identity authentication method and system based on movement track Download PDFInfo
- Publication number
- CN114827902A CN114827902A CN202210223846.6A CN202210223846A CN114827902A CN 114827902 A CN114827902 A CN 114827902A CN 202210223846 A CN202210223846 A CN 202210223846A CN 114827902 A CN114827902 A CN 114827902A
- Authority
- CN
- China
- Prior art keywords
- entity
- track
- authentication
- model
- legal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000003068 static effect Effects 0.000 claims abstract description 12
- 238000010801 machine learning Methods 0.000 claims description 21
- 238000005516 engineering process Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000013500 data storage Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 230000006403 short-term memory Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000011161 development Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- 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
- G06N3/048—Activation functions
-
- 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
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
- H04W12/065—Continuous authentication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
- H04W12/126—Anti-theft arrangements, e.g. protection against subscriber identity module [SIM] cloning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/63—Location-dependent; Proximity-dependent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides an identity authentication method and system based on a movement track, belongs to the technical field of Internet of things safety, and can perform equipment authentication or user authentication according to the movement track of equipment, identify an illegal entity and require the entity to perform secondary identity authentication. The method fully utilizes the position sequence dependency relationship among all points in the equipment moving track as the behavior pattern characteristics of the entity, thereby dynamically carrying out the matching authentication of the track and the entity identity. The system is suitable to be used as an auxiliary identity authentication system, is matched with the existing static identity authentication system for use, and is applied to various IoT scenes using mobile equipment, so that the safety problems of the Internet of things such as equipment theft, identity hijack and the like are relieved, and the safety of the Internet of things is enhanced.
Description
Technical Field
The invention relates to an identity authentication method and system based on a movement track, and belongs to the technical field of Internet of things safety.
Background
With the development of internet of things (IoT) technology, the problem of device security management has come to the fore. The device authentication and the user authentication (hereinafter, collectively referred to as entity authentication) are important components of the security management technology of the internet of things. Early internet of things was mainly implemented based on a local area network, which was isolated from the internet by a gateway, while the devices and users inside the local area network were relatively trusted. Therefore, the security requirements for entity authentication by the early internet of things are low. With the development of the mobile internet, a plurality of mobile devices are linked into the internet of things through the internet, and the anonymity and connectivity of the internet greatly reduce the safety of the internet of things, so that the internet of things provides higher safety requirements for the authentication technology.
At present, the user authentication technology has been greatly developed and popularized, and compared with the traditional password authentication, the biometric identification technology provides higher security guarantee; in the field of device identity authentication, password authentication techniques represented by device identifiers are mainly used at present. However, these techniques all belong to static security authentication, i.e. one-time authentication, and the authentication system defaults to the validity of the access entity. Once the entity passes the authentication, the system will not question the validity of the entity identity even if there is subsequent illegal operation. This is not enough to accommodate some IoT scenarios where security requirements are high.
Disclosure of Invention
In view of the above technical problems, an object of the present invention is to provide an identity authentication method and system for a mobile device, which can perform device authentication or user authentication according to a device movement trajectory, identify an illegal entity, and request the entity to perform secondary identity authentication. The technology is suitable for serving as an auxiliary identity authentication method, is matched with the existing static identity authentication method for use, and is applied to various IoT scenes using mobile equipment, so that the safety problems of the Internet of things such as equipment theft, identity hijack and the like are relieved.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
an identity authentication method based on a movement track comprises the following steps:
1) recording the moving tracks of equipment under the control of all legal entities in a target area, wherein the moving tracks are sequences of a plurality of position coordinate points which are ordered according to time sequence, the moving tracks are used as legal moving tracks, and each legal moving track is marked by the entity number of the entity generating the track;
2) training a multi-classification machine learning model by utilizing a legal movement track and a corresponding entity number, and outputting the probability distribution of an entity to which the movement track belongs according to a position vector on the legal movement track and the entity number by the machine learning model;
3) recording the current moving track of the target equipment in operation;
4) inputting the current movement track information of the target equipment into a machine learning model, extracting the sequence dependency relationship information of the midpoint of the current movement track by the machine learning model according to the position vector of the current movement track, outputting the probability of each entity number corresponding to the current movement track according to the sequence dependency relationship information of the midpoint of the current movement track, matching the entity identity declared by the owner of the target equipment with the first entity numbers with the highest probability output by the machine learning model, if matching, successfully authenticating, otherwise, failing to authenticate.
Further, one or two positioning modes of satellite navigation positioning and base station-based positioning are used for obtaining a legal movement track and a current movement track.
Furthermore, when the movement track is recorded, the target area space is divided into a plurality of grids, the position point data of the equipment is converted into uniform space grid numbers, and the legal movement track is formed by the passing space grid numbers.
Furthermore, embedding each position point on the movement track of the equipment by using the skip-gram technology of the word2vec model to form a position vector.
Further, the machine learning model includes a markov chain model, a one-way long short term memory model (LSTM), or a two-way long short term memory model.
Further, when an LSTM model is used as the machine learning model, the model is constructed based on a multi-layered perceptron MLP, the activation function is ReLU, and the model is trained using a cross entropy loss function.
Further, for the authentication failure, if the target equipment is equipment for man-machine interaction, the static identity authentication technology is used for requiring the holder of the target equipment to carry out secondary identity authentication, wherein the secondary identity authentication comprises password authentication and biological fingerprint information authentication; otherwise, the target equipment holder is required to provide the equipment number or the password again for secondary identity authentication.
An identity authentication system based on a moving track comprises a server side and a client side, wherein the server side comprises an entity registration module, a track data storage module, a model training and authentication module and a communication module; the client comprises a position information acquisition module, an alarm module and a communication module; wherein:
the entity registration module is used for registering all entities in the target area and distributing a unique entity number for each entity;
the track data storage module is used for maintaining a device moving track information data set, and storing and adding legal moving track information from the client;
the model training and authentication module is used for training a multi-classification machine learning model by utilizing a legal movement track and a corresponding entity number and maintaining the update iteration of the model; the model is used for carrying out identity recognition on the current moving track submitted by the client and comparing the current moving track with the entity number declared by the client, so that whether the current moving track is a declared legal user or not is judged;
the position information acquisition module is used for acquiring position points of the mobile equipment and converting different types of position data into unified grid coordinate representation;
the alarm module is used for requiring the entity to perform secondary identity authentication by using the existing static identity authentication technology;
the communication module is used for realizing data interaction between the client and the server.
The basic principle of the technical scheme of the invention is as follows: and (3) establishing a model by using the normal movement track data of the legal entity and combining a machine learning technology, and identifying the identity of the entity by using the model according to the current track so as to judge whether the current entity is consistent with the declared identity of the current entity during static authentication. The invention has the following beneficial effects: 1) the identity of the entity is dynamically, spontaneously and periodically authenticated through the moving track, so that the method can be used as a supplement of a static identity authentication technology in the Internet of things, and the safety of the Internet of things is further improved. 2) The position points are represented by uniform grid coordinates, so that different positioning technologies and different position information types acquired by positioning equipment in the Internet of things are compatible. 3) The confidence threshold may be adjusted according to different IoT scenarios, providing different levels of fault tolerance authentication. 4) The method disclosed by the invention is not only based on each point in the track during authentication, but also depends on the sequence dependency relationship of the midpoint in the track, and compared with the traditional track processing mode, the method can independently use each position point (for example, judging the proximity degree of the ith position point in the two tracks).
Drawings
FIG. 1 is a block diagram of a mobile trajectory-based identity authentication system of the present invention;
FIG. 2 is a flowchart of the operation of an identity authentication system based on a movement trajectory according to the present invention;
fig. 3 is a unified grid representation of location information in accordance with the present invention.
Detailed Description
In order to make the aforementioned and other features and advantages of the invention more comprehensible, embodiments accompanied with figures are described in detail below.
The embodiment of the invention provides an identity authentication system based on a moving track, which specifically comprises a server and a client, wherein the server comprises an entity registration module, a track data storage module, a model training and authentication module and a communication module; the client is deployed in the mobile equipment and comprises a position information acquisition module, an alarm module and a communication module; wherein:
1) the entity registration module registers each entity and assigns a unique entity number to it.
2) And the track data storage module maintains a track information data set, and stores and adds a legal moving track from the client.
3) The communication module provides data interaction support for the client and the server;
4) position information acquisition module
The system first selects a region (which may be a block or the entire earth) and divides the region into a number of two-dimensional grids. The position information acquisition module acquires longitude and latitude information from a satellite positioning system or acquires position information through a base station; then placing the original position points into a grid according to the geographical position, and representing the position points by using the grid coordinates of the points and the acquisition time of the points; finally, the module sends the location data to the server while declaring its own entity number.
5) Model training and certification module
The module takes a track formed by the position points in a time sequence in a link mode as input data, takes the number of an entity generating the track as a label, and trains a multi-classification machine learning model. The model may have a variety of options including, but not limited to, Markov chain, one-way/two-way LSTM, etc. In order to improve the fault-tolerant capability of the system, the model gives the first k entity numbers with the highest possibility when entity identification is carried out on a track, and as long as the entity identity (such as an identity card number, a unique identification number distributed during user registration, an equipment identification code and the like) declared by equipment is one of the k numbers, the authentication is considered to be successful. The value of k can be adjusted according to the IoT scene needs, k can be set to a smaller value in a high security requirement scene, and a larger value of k can be set in a low security requirement scene.
6) Alarm module
The module triggers the static authentication system of the device after receiving the warning from the server side. If the device is used for man-machine interaction, the user is required to perform static secondary identity authentication, including password authentication, biometric fingerprint information authentication and the like; otherwise, the equipment number or the password is required to be provided again for secondary identity authentication.
The working flow of the system is shown in fig. 2, and is specifically explained as follows:
1) and the server distributes entity numbers for all legal entities, and trains the multi-classification machine learning model according to the trajectory data and the entity numbers generated by the entities.
2) The client acquires the position points of the mobile equipment in real time, converts the position points into grid coordinate representation, submits the grid coordinate representation to the server, and simultaneously declares the identity of the client, namely the entity number.
3) And the server judges the entity identity of the track submitted by the client according to the model, and compares the entity identity with the declared entity number to realize identity authentication.
4) If the identity authentication is successful, the server can choose to incorporate the trajectory and the entity number into a training set for subsequent model iteration updating.
5) If the authentication fails, the server notifies an alarm module of the client, so that the device requires static authentication.
The following description will be given taking a mobile phone application scenario as an example.
Under a scenario, the identity authentication system based on the movement track provided by the invention is used for mobile phone user authentication in a town.
In the initialization stage, the system divides the town into m multiplied by n grids according to the geographic position, and simultaneously deploys the client as a continuously running component in the mobile phone; meanwhile, the authentication service provider deploys a data center and a service end, and allocates a unique identification number, namely an entity number, to each mobile phone. The mobile phone continuously records the position of the mobile phone through a positioning system, simultaneously converts the geographic position data into grid numbers according to the mode, and then sends the position points generated in the same day and the unique identification number of the mobile phone to the server side together. As shown in FIG. 3, c 1～8 、r 1～8 Is a divided grid, p 1 、p 2 Are location points located by satellite or base stations, which may be defined by a corresponding grid g 1 、g 2 Is represented by g 1 ＝(r 2 ,c 7 )，g 2 ＝(r 4 ,c 3 )。
The server side trains a multi-classification machine learning model by using the track data generated by all the client sides in the initialization stage, and establishes the mapping from the track to the entity number, wherein the specific mode is as follows:
1) and embedding the position points by using a skip-gram technology of a word2vec model in the field of natural language processing to form a position vector.
2) Taking the position vector as input, extracting sequence dependence information in the track by using an LSTM model, and recording the final output of the LSTM as h out 。
3) Sequence information h output by LSTM out And constructing a multi-classification machine learning model by using a multi-layer perceptron (MLP) for input, and outputting probability distribution of the entity to which the track belongs. ReLU is used as an activation function in MLP, and the model is trained with a cross entropy loss function.
Wherein u is the set of all entities, T is the set of all traces in the training set, and the absolute value symbol represents the number of elements in the set. u. of j Is the numbered one-hot form of the jth entity in u. T is a unit of i ' is the recognition result of the ith trajectory by the model, which is in the form of a vector whose k-th element is the probability that the trajectory is generated by the k-th entity. Due to T i ' is a probability vector with a sum of 1, so the log base is taken as the value of the interval (0, 1).
In the operation stage, the mobile phone records the position point in the same way as above and sends the position point to the server together with the unique identification number of the mobile phone. And the server takes the track submitted by the client as input, classifies the track by using the model, and outputs a result which represents the probability of each identification number corresponding to the track in a probability vector mode. And sorting according to the probability from high to low, and selecting the first five identification numbers with the highest probability as the real identities corresponding to the tracks. The server compares the mobile handset with the device's asserted identity number, and if the device's asserted identity number is one of the five identity numbers, the mobile handset is considered to be currently held by a legitimate user. Otherwise, the current holder of the mobile phone is considered to be not a legal user, and the server warns the client at the moment, so that the mobile phone initiates one-time independent authentication on the user in a secondary password mode, and the mobile phone is prevented from being stolen or stolen.
Although the present invention has been described with reference to the above embodiments, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. An identity authentication method based on a movement track is characterized by comprising the following steps:
recording the moving tracks of equipment under the control of all legal entities in a target area, wherein the moving tracks are sequences of a plurality of position coordinate points which are ordered according to time sequence, the moving tracks are used as legal moving tracks, and each legal moving track is marked by the entity number of the entity generating the track;
training a multi-classification machine learning model by utilizing a legal movement track and a corresponding entity number, and outputting probability distribution of an entity to which the movement track belongs by the machine learning model according to a position vector on the legal movement track and the entity number;
recording the current moving track of the target equipment in operation;
inputting the current movement track information of the target equipment into a machine learning model, extracting the sequence dependency relationship information of the midpoint of the current movement track by the machine learning model according to the position vector of the current movement track, outputting the probability of each entity number corresponding to the current movement track according to the sequence dependency relationship information of the midpoint of the current movement track, matching the entity identity declared by the owner of the target equipment with the first entity numbers with the highest probability output by the machine learning model, if matching, successfully authenticating, otherwise, failing to authenticate.
2. The method of claim 1, wherein the legal movement trajectory and the current movement trajectory are obtained using one or both of satellite navigation positioning, base station based positioning, and the like.
3. The method of claim 1, wherein when recording the movement trajectory, the target area space is divided into a plurality of grids, the position point data of the device is converted into a uniform spatial grid number, and the legal movement trajectory is formed by the spatial grid number passed through.
4. The method of claim 1, wherein each location point on the movement trajectory of the device is embedded using a skip-gram technique of the word2vec model to generate a location vector.
5. The method of claim 1, in which the machine learning model comprises a Markov chain model, a one-way long short term memory model (LSTM), or a two-way long short term memory model.
6. The method of claim 5, wherein when using an LSTM model as the machine learning model, the model is constructed based on multi-layered perceptron MLP, the activation function is ReLU, and the model is trained using a cross-entropy loss function.
7. The method of claim 6, wherein the cross-entropy loss function is as follows:
where u is the set of all entities and T is the training setIn the set of all tracks, the absolute value symbol represents the number of elements in the set; u. of j Is a one-hot form of the number of the jth entity in u; t is i ' is the recognition result of the model to the ith track; the log base takes the value of the interval (0, 1).
8. The method of claim 1, wherein for authentication failure, if the target device is a device for human-computer interaction, the target device holder is required to perform secondary authentication using static authentication techniques, the secondary authentication including password authentication and biometric fingerprint information authentication; otherwise, the target equipment holder is required to provide the equipment number or the password again for secondary identity authentication.
9. An identity authentication system based on a movement track for realizing the method of any one of claims 1 to 8, which is characterized by comprising a server side and a client side, wherein the server side comprises an entity registration module, a track data storage module, a model training and authentication module and a communication module; the client comprises a position information acquisition module, an alarm module and a communication module; wherein:
the entity registration module is used for registering all entities in the target area and distributing a unique entity number for each entity;
the track data storage module is used for maintaining a device moving track information data set, and storing and adding legal moving track information from the client;
the model training and authentication module is used for training a multi-class machine learning model by utilizing a legal movement track and a corresponding entity number and maintaining the update iteration of the model; the model is used for carrying out identity recognition on the current moving track submitted by the client and comparing the current moving track with the entity number declared by the client, so that whether the current moving track is a declared legal user or not is judged;
the position information acquisition module is used for acquiring position points of the mobile equipment and converting different types of position data into unified grid coordinate representation;
the alarm module is used for requiring the entity to perform secondary identity authentication by using the existing static identity authentication technology;
the communication module is used for realizing data interaction between the client and the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210223846.6A CN114827902A (en) | 2022-03-09 | 2022-03-09 | Identity authentication method and system based on movement track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210223846.6A CN114827902A (en) | 2022-03-09 | 2022-03-09 | Identity authentication method and system based on movement track |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114827902A true CN114827902A (en) | 2022-07-29 |
Family
ID=82529333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210223846.6A Pending CN114827902A (en) | 2022-03-09 | 2022-03-09 | Identity authentication method and system based on movement track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827902A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090324010A1 (en) * | 2008-06-26 | 2009-12-31 | Billy Hou | Neural network-controlled automatic tracking and recognizing system and method |
| US20160253490A1 (en) * | 2013-10-30 | 2016-09-01 | Ohio University | Motion-based identity authentication of an individual |
| CN109286499A (en) * | 2018-09-21 | 2019-01-29 | 武汉大学 | A kind of authentication method on the scene of Behavior-based control feature |
| CN109871444A (en) * | 2019-01-16 | 2019-06-11 | 北京邮电大学 | A kind of file classification method and system |
| CN112653995A (en) * | 2019-10-12 | 2021-04-13 | 中国移动通信有限公司研究院 | User identity recognition method and device and computer readable storage medium |
| CN113312596A (en) * | 2021-06-10 | 2021-08-27 | 重庆市勘测院 | User identity recognition method based on deep learning and asynchronous track data |
-
2022
- 2022-03-09 CN CN202210223846.6A patent/CN114827902A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090324010A1 (en) * | 2008-06-26 | 2009-12-31 | Billy Hou | Neural network-controlled automatic tracking and recognizing system and method |
| US20160253490A1 (en) * | 2013-10-30 | 2016-09-01 | Ohio University | Motion-based identity authentication of an individual |
| CN109286499A (en) * | 2018-09-21 | 2019-01-29 | 武汉大学 | A kind of authentication method on the scene of Behavior-based control feature |
| CN109871444A (en) * | 2019-01-16 | 2019-06-11 | 北京邮电大学 | A kind of file classification method and system |
| CN112653995A (en) * | 2019-10-12 | 2021-04-13 | 中国移动通信有限公司研究院 | User identity recognition method and device and computer readable storage medium |
| CN113312596A (en) * | 2021-06-10 | 2021-08-27 | 重庆市勘测院 | User identity recognition method based on deep learning and asynchronous track data |
Non-Patent Citations (3)
| Title |
|---|
| 王嘉强;范延滨;: "基于LSTM模型的人体情景多标签识别研究", 青岛大学学报(工程技术版), no. 04, 11 December 2018 (2018-12-11) * |
| 符晨曦;程钢;董文帅;岳俊升;张清兰;: "一种基于智能移动终端的家庭成员安全监护系统设计与实现", 测绘工程, no. 12, 23 November 2018 (2018-11-23) * |
| 陈鸿昶;徐乾;黄瑞阳;程晓涛;吴铮;: "一种基于用户轨迹的跨社交网络用户身份识别算法", 电子与信息学报, no. 11, 3 July 2018 (2018-07-03) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lu et al. | Lip reading-based user authentication through acoustic sensing on smartphones | |
| US11836643B2 (en) | System for secure federated learning | |
| US11244146B2 (en) | Systems and methods for secure user logins with facial recognition and blockchain | |
| WO2021043014A1 (en) | Identity authentication method based on biometric feature, and identity authentication system thereof | |
| CN104036780A (en) | Man-machine identification method and system | |
| CN106600243A (en) | Mobile payment method and system based on mixed mode | |
| CN112084476A (en) | Biological identification identity verification method, client, server, equipment and system | |
| CN114095931B (en) | Sparse track space-time characteristic-based access detection method and device in satellite-ground communication | |
| Abdalzaher et al. | Toward secured iot-based smart systems using machine learning | |
| Kamruzzaman et al. | AI-based computer vision using deep learning in 6G wireless networks | |
| CN114004639B (en) | Method, device, computer equipment and storage medium for recommending preferential information | |
| CN105099700A (en) | Authentication method, authentication server, and system | |
| CN107453803B (en) | A kind of abnormal check method of remote sensing cloud core | |
| Mo et al. | Random forest based coarse locating and KPCA feature extraction for indoor positioning system | |
| CN114827902A (en) | Identity authentication method and system based on movement track | |
| Lee et al. | Robust face anti-spoofing framework with Convolutional Vision Transformer | |
| CN116824676A (en) | Digital identity information generation method, application method, device, system and equipment | |
| US20220029972A1 (en) | Systems and methods for providing a systemic error in artificial intelligence algorithms | |
| Alsultan et al. | A comparative study of biometric authentication in cloud computing | |
| CA3195434A1 (en) | Systems and methods for providing a systemic error in artificial intelligence algorithms | |
| Liu | Fingerprint analysis and singular point definition by deep neural network | |
| CN117494092B (en) | Scenic spot ticket non-inductive verification method, system and medium based on living organism identification | |
| US11973743B2 (en) | Systems and methods for providing a systemic error in artificial intelligence algorithms | |
| CN113704733B (en) | Privacy verifiable dynamic DID authentication method and system | |
| KR20180099149A (en) | Attendance check system and method using bluetooth and fingerprint sensor of smart device |
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 |