CN103699822A - Application system and detection method for users' abnormal behaviors in e-commerce based on mouse behaviors - Google Patents
Application system and detection method for users' abnormal behaviors in e-commerce based on mouse behaviors Download PDFInfo
- Publication number
- CN103699822A CN103699822A CN201310747420.1A CN201310747420A CN103699822A CN 103699822 A CN103699822 A CN 103699822A CN 201310747420 A CN201310747420 A CN 201310747420A CN 103699822 A CN103699822 A CN 103699822A
- Authority
- CN
- China
- Prior art keywords
- user
- mouse
- data
- proper vector
- behavior
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/316—User authentication by observing the pattern of computer usage, e.g. typical user behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to an application system and a detection method for users' abnormal behaviors in e-commerce based on mouse behaviors. The application system comprises a B2C (business to customer) e-commerce website, a mouse behavior data acquisition module, a detection module and a database. The method includes two steps of normal user mode extraction and matching detection. Specific to special application environments, personalized mouse behavior feature vectors are designed, reliability in identity authentication is enhanced, and transaction safety of e-commerce is guaranteed.
Description
Technical field
The invention belongs to the authentication householder method based on mouse behavior.
Background technology
Along with the continuous progress of society, internet just with qualitative leap in development, the ecommerce of carrying out commodity and service marketing by network thereupon occurring has become the irresistible trend of global enterprise.From 1997 so far, the ecommerce of China is vigorously grown up, and Deng Ji home Web site of group of Alibaba competition from initial, has developed into the state of nowadays letting a hundred schools contend, attracts increasing people to conduct business activities by network trading and online payment.
Security is a vital key problem in ecommerce, and it requires network that a kind of security solution end to end can be provided.For website, go fishing, also different Prevention Technique means have been there are, as filtrating mail (IE7 that Microsoft releases), E-mail authentication (the Sender ID Framework that Microsoft releases, the DK plan that Yahoo is used), Standford University proposes two kinds of prevention method PwdHash and SpoofGuard based on browser client, and the technology such as SSL digital certificate.The technology emphasis of these means is all positioned at above strick precaution, and object is to prevent user to suffer phishing attack.In order to protect the user's who is subject to phishing attack rights and interests, the Authentication Questions that solves user is also necessary, thereby on technological layer, guarantees that the user of participation network transaction is " trusted users ".
This patent towards situation be in network trading, generally to adopt the method for digital certificate to carry out authentication at present, the maximum drawback of this mechanism is exactly that the information such as password are easily revealed, and exists serious potential safety hazard.When password is simpler, by the Brute Force based on dictionary, just can crack.While is due to the information leakage of phishing and regular website, hacker can obtain user's digital certificate, and then fake user identity carries on business, therefore adopt digital certificate mode can not ideally solve the believable problem of user identity, there is certain defect.
Summary of the invention
The object of the invention is to disclose user's anomaly detection method in a kind of ecommerce based on mouse behavior, and for application circumstances, the mouse behavioural characteristic of design personalized vector, strengthens authentication reliable, guarantees the transaction security of ecommerce.
The technical scheme that the present invention provides is:
The application system that in ecommerce based on mouse behavior, user's abnormal behaviour detects, is characterized in that,
Comprise B2C electricity business website, for user provides shopping environment;
Comprise mouse behavioral data acquisition module, the data that produce for collecting user's shopping process operating mouse; Described mouse behavioral data acquisition module is embedded in e-commerce website, uses JavaScript script.The data item gathering during mouse-click mainly contains: page sequence number, X, Y-axis coordinate figure, timestamp etc.Data when collection mouse moves, need to preset a sampling rate, image data comprises page sequence number, X, Y-axis coordinate figure, timestamp, translational speed, acceleration, move angle values etc., wherein latter three cannot directly gather, need to be by the raw data gathering is drawn through a series of mathematical operations.
Comprise detection module, utilize the mouse data that cluster scheduling algorithm collects training period to carry out solidifying of normal behaviour pattern, active user's behavior pattern is calculated to generation, finally carry out matching detection operation.
Comprise database, the data that produce at user's shopping process operating mouse for storing data acquisition module offer standby normal behaviour pattern detection module for to carrying out matching detection with active user's behavior pattern simultaneously.
In ecommerce based on mouse behavior, user's anomaly detection method, is characterized in that,
Step 1, normal user mode is extracted: the normal mouse behavioral data to training period collection carries out pre-service, utilizes the methods such as K-means clustering algorithm based on Euclidean distance, extracts user's normal behaviour pattern.
Step 2, matching detection: active user's mouse data is carried out to same treatment, obtain active user's mouse behavior pattern, carry out the matching analysis with normal mode.
The invention belongs to the identity identifying method based on mouse behavior, is by the behavioural characteristic of this computer entry device of research mouse, identifies user's identity.This authentication method can be studied user's mouse behavior from man-machine interaction and physiology aspect.
Mouse behavioral data acquisition module, by the Real-time Collection user data that operating mouse equipment moving produces in carrying out ecommerce process, and extracts and stores necessary data message by the mathematical computations of certain step.
User's mouse behavior detection system is extracted and two module compositions of active user's behavior matching detection by normal user mode.Normal user mode extraction module, carries out pre-service to the normal mouse behavioral data of training period collection, utilizes the methods such as K-means clustering algorithm based on Euclidean distance, extracts user's normal behaviour pattern.Active user's behavior matching detection module, carries out same treatment to active user's mouse data, obtains active user's mouse behavior pattern, carries out the matching analysis with normal mode, thereby whether extremely judgement user behavior.
Innovative point of the present invention and beneficial effect:
1, will in computer system, based on mouse behavior, carry out the thought of authentication, be used in user's abnormal behaviour detection of ecommerce, as the supplementary means of digital authenticating.
2, in conjunction with the flow process of user's shopping in ecommerce, a kind of detection model of using for reference automat idea is proposed.
3, for application circumstances, the mouse behavioural characteristic of design personalized vector.
Accompanying drawing explanation
Below in conjunction with drawings and embodiments, the present invention is described in further detail:
Fig. 1 is entire system Organization Chart;
Fig. 2 is window coordinates systems;
Fig. 3 is detection model;
Fig. 4 is the extraction process flow diagram of proper vector;
Fig. 5 is matching detection process flow diagram.
Embodiment
As shown in Figure 1, 2: B2C electricity business website is for analog subscriber shopping environment, the data that in user's shopping process, operating mouse produces are collected and stored to mouse behavioral data acquisition module, detection module utilizes the mouse data that cluster scheduling algorithm collects training period to carry out solidifying of normal behaviour pattern, active user's behavior pattern is calculated to generation, finally carry out matching detection operation.
Mouse behavioral data acquisition module is embedded in e-commerce website, uses JavaScript script.The data item gathering during mouse-click mainly contains: page sequence number, X, Y-axis coordinate figure, timestamp etc.Data when collection mouse moves, need to preset a sampling rate, image data comprises page sequence number, X, Y-axis coordinate figure, timestamp, translational speed, acceleration, move angle values etc., wherein latter three cannot directly gather, need to be by the raw data gathering is obtained through a series of mathematical operation youngsters.The coordinate system that adopts lower Fig. 2 to set up during image data.
As shown in Figure 3: the principle of work of detection module is that while selecting user to do shopping operation in electric business website, what occur really may have the ordering behavior of substantive injury to analyze to user benefit.Specifically as shown in Figure 3, this detection model has been used for reference the idea of state set, input character and transfer function in automat, and each circle represents a state, and arrow represents transfer function, and symbol 1 and 0 represents that respectively whether behavior pattern mate.While shifting each time, all need to use the proper vector of customization, be respectively FeatureVector0, FeatureVector1, FeatureVector2, FeatureVector3.When active user's behavior is detected, the proper vector generating is mated, while once shifting arbitrarily, coupling exceeds certain threshold value, is all directly judged as abnormal.
As shown in Figure 4: the design of proper vector, utilize the data that collect, consider that applied environment is ecommerce shopping website, for embodying characteristic, therefore each state transition has the proper vector that oneself customizes in shopping process simultaneously.Particularly, as when logging status shifts, the length, input difficulty, input hand speed etc. of considering each user's user name and password are different, user is clicked to mistiming between user name text box, cryptogram frame and login button as a part for proper vector, get its mean value as eigenwert; On the other hand, the click region of user when clicking login button also varies with each individual, this coordinate figure is also elected a part for proper vector as, by a large amount of click-point coordinates that collect, by the K-Means clustering algorithm based on Euclidean distance, obtain the coordinate figure of bunch heart coordinate of dense cluster as eigenwert.Be defined as FeatureVector0=(T1, T2, Point), wherein T1 represents to click the mistiming between user name text box and cryptogram frame, T2 represents to click the mistiming between cryptogram frame and login button, and Point is bunch heart coordinate points data of intensive several bunches.Browsing while choosing state, different user hobby is different, and physiologic habit is different, will frequently click region and mouse translational speed, acceleration, move angle value etc. all as proper vector.Definition FeatureVector1=(Point, v, a, angle), wherein Point is the most intensive bunch heart coordinate points data acquisition of several bunches of click-point distribution, v represents minimum value, maximal value and the densely distributed mean value array of translational speed, and a represents maximal value and the densely distributed mean value array of translational acceleration, and angle represents the densely distributed value array of move angle value.
As shown in Figure 5: the idiographic flow of matching detection is as shown below.During coupling, the direct distance between calculated characteristics vector, because each component of each proper vector is different, therefore ask respectively the distance between the component of same type, surpass certain threshold value (threshold value is drawn by abundant experimental results and summary of experience), be judged as abnormal.
Claims (6)
1. the application system that in the ecommerce based on mouse behavior, user's abnormal behaviour detects, is characterized in that,
Comprise B2C electricity business website, for user provides shopping environment;
Comprise mouse behavioral data acquisition module, the data that produce for collecting user's shopping process operating mouse; Described mouse behavioral data acquisition module is embedded in e-commerce website, uses JavaScript script;
The data item gathering during mouse-click mainly contains: page sequence number, X, Y-axis coordinate figure, timestamp etc.;
Data when collection mouse moves, need to preset sampling rate, and image data comprises page sequence number, X, Y-axis coordinate figure, timestamp, translational speed, acceleration, move angle value etc., wherein rear three need to be by the raw data gathering be drawn after indirect mathematical operation;
Comprise detection module, utilize the mouse data that cluster scheduling algorithm collects training period to carry out solidifying of normal behaviour pattern, active user's behavior pattern is calculated to generation, finally carry out matching detection operation;
Comprise database, the data that produce at user's shopping process operating mouse for storing data acquisition module offer standby normal behaviour pattern detection module for to carrying out matching detection with active user's behavior pattern simultaneously.
2. user's anomaly detection method in the ecommerce based on mouse behavior, is characterized in that,
Step 1, normal user mode is extracted: the normal mouse behavioral data to training period collection carries out pre-service, utilizes the methods such as K-means clustering algorithm based on Euclidean distance, extracts user's normal behaviour pattern;
Step 2, matching detection: active user's mouse data is carried out to same treatment, obtain active user's mouse behavior pattern, carry out the matching analysis with normal mode.
3. user's anomaly detection method in the ecommerce based on mouse behavior according to claim 2, is characterized in that, it is to adopt the method for extracting proper vector to realize that described pattern is extracted, and specifically comprises:
Pretreatment stage, carries out clustering processing rejecting abnormalities point to image data coordinate points;
The generate pattern stage, according to proper vector definition, calculate, and to database storage proper vector;
More the new stage, the pretreatment stage that is circulated to of not timing is optimized renewal to proper vector.
4. user's anomaly detection method in the ecommerce based on mouse behavior according to claim 2, is characterized in that, described matching detection, and its method is:
During coupling, the direct distance between calculated characteristics vector, because each component of each proper vector is different, therefore ask respectively the distance between the component of same type;
Surpass certain threshold value (threshold value is drawn by abundant experimental results and summary of experience), be judged as abnormal.
5. user's anomaly detection method in the ecommerce based on mouse behavior according to claim 3, it is characterized in that, the design of described proper vector, utilize the data that collect, consider that applied environment is ecommerce shopping website simultaneously, for embodying characteristic, therefore each state transition has the proper vector that oneself customizes in shopping process;
Particularly, as when logging status shifts, the length, input difficulty, input hand speed etc. of considering each user's user name and password are different, user is clicked to mistiming between user name text box, cryptogram frame and login button as a part for proper vector, get its mean value as eigenwert; On the other hand, the click region of user when clicking login button also varies with each individual, this coordinate figure is also elected a part for proper vector as, by a large amount of click-point coordinates that collect, by the K-Means clustering algorithm based on Euclidean distance, obtain the coordinate figure of bunch heart coordinate of dense cluster as eigenwert;
Be defined as FeatureVector0=(T1, T2, Point), wherein T1 represents to click the mistiming between user name text box and cryptogram frame, T2 represents to click the mistiming between cryptogram frame and login button, and Point is bunch heart coordinate points data of intensive several bunches;
Browsing while choosing state, different user hobby is different, and physiologic habit is different, will frequently click region and mouse translational speed, acceleration, move angle value etc. all as proper vector;
Definition FeatureVector1=(Point, v, a, angle), wherein Point is the most intensive bunch heart coordinate points data acquisition of several bunches of click-point distribution, v represents minimum value, maximal value and the densely distributed mean value array of translational speed, and a represents maximal value and the densely distributed mean value array of translational acceleration, and angle represents the densely distributed value array of move angle value.
6. user's anomaly detection method in the ecommerce based on mouse behavior according to claim 2, it is characterized in that, described matching detection, that while selecting user to do shopping operation in electric business website, what occur really may have the ordering behavior of substantive injury to analyze to user benefit;
This detection model has been used for reference the idea of state set, input character and transfer function in automat, and each circle represents a state, and arrow represents transfer function, and symbol 1 and 0 represents that respectively whether behavior pattern mate;
While shifting each time, all need to use the proper vector of customization, be respectively FeatureVector0, FeatureVector1, FeatureVector2, FeatureVector3;
When active user's behavior is detected, the proper vector generating is mated, while once shifting arbitrarily, coupling exceeds certain threshold value, is all directly judged as abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310747420.1A CN103699822B (en) | 2013-12-31 | 2013-12-31 | User's anomaly detection method in ecommerce based on mouse behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310747420.1A CN103699822B (en) | 2013-12-31 | 2013-12-31 | User's anomaly detection method in ecommerce based on mouse behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103699822A true CN103699822A (en) | 2014-04-02 |
| CN103699822B CN103699822B (en) | 2016-11-02 |
Family
ID=50361349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310747420.1A Active CN103699822B (en) | 2013-12-31 | 2013-12-31 | User's anomaly detection method in ecommerce based on mouse behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103699822B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281795A (en) * | 2014-09-25 | 2015-01-14 | 同济大学 | Mouse action based password fault tolerance method |
| CN104318435A (en) * | 2014-09-25 | 2015-01-28 | 同济大学 | Immunization method for user behavior detection in electronic transaction process |
| CN104881594A (en) * | 2015-05-06 | 2015-09-02 | 镇江乐游网络科技有限公司 | Smartphone ownership detection method based on accurate figure |
| CN105976201A (en) * | 2016-04-28 | 2016-09-28 | 北京小米移动软件有限公司 | Purchase behavior monitoring method for electronic business system and device |
| CN106156362A (en) * | 2016-08-01 | 2016-11-23 | 陈包容 | A kind of method and device automatically providing solution for early warning |
| CN106339316A (en) * | 2016-08-24 | 2017-01-18 | 上海爱企网络科技有限公司 | Method and device for diagnosing code segment in e-commerce platform |
| CN106384027A (en) * | 2016-09-05 | 2017-02-08 | 四川长虹电器股份有限公司 | User identity recognition system and recognition method thereof |
| CN106817342A (en) * | 2015-11-30 | 2017-06-09 | 北京计算机技术及应用研究所 | Active identity authorization system based on user behavior feature recognition |
| CN107122641A (en) * | 2017-04-25 | 2017-09-01 | 杭州安石信息技术有限公司 | Smart machine owner recognition methods and owner's identifying device based on use habit |
| CN107335220A (en) * | 2017-06-06 | 2017-11-10 | 广州华多网络科技有限公司 | A kind of recognition methods of passive user, device and server |
| CN107395562A (en) * | 2017-06-14 | 2017-11-24 | 广东网金控股股份有限公司 | A kind of financial terminal security protection method and system based on clustering algorithm |
| CN107908300A (en) * | 2017-11-17 | 2018-04-13 | 哈尔滨工业大学（威海） | A kind of synthesis of user's mouse behavior and analogy method and system |
| CN109407947A (en) * | 2018-09-30 | 2019-03-01 | 北京金山云网络技术有限公司 | Interface alternation and its verification method, logging request generation and verification method and device |
| CN111917801A (en) * | 2020-08-18 | 2020-11-10 | 南京工业大学浦江学院 | Petri network-based user behavior authentication method in private cloud environment |
| CN113569656A (en) * | 2021-07-02 | 2021-10-29 | 广州大学 | Examination room monitoring method based on deep learning |
| CN117194202A (en) * | 2023-11-08 | 2023-12-08 | 北京网藤科技有限公司 | System and method for detecting user operation dilemma based on webpage mouse behaviors |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004097601A1 (en) * | 2003-05-02 | 2004-11-11 | Ahmed Awad El-Sayed Ahmed | System and method for determining a computer user profile from a motion-based input device |
| CN1957355A (en) * | 2004-04-01 | 2007-05-02 | 道夫·雅各布森 | Mouse performance identification |
| EP2490149A1 (en) * | 2011-02-17 | 2012-08-22 | Deutsche Telekom AG | System for verifying user identity via mouse dynamics |
-
2013
- 2013-12-31 CN CN201310747420.1A patent/CN103699822B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004097601A1 (en) * | 2003-05-02 | 2004-11-11 | Ahmed Awad El-Sayed Ahmed | System and method for determining a computer user profile from a motion-based input device |
| CN1957355A (en) * | 2004-04-01 | 2007-05-02 | 道夫·雅各布森 | Mouse performance identification |
| EP2490149A1 (en) * | 2011-02-17 | 2012-08-22 | Deutsche Telekom AG | System for verifying user identity via mouse dynamics |
Non-Patent Citations (2)
| Title |
|---|
| 房超等: "基于鼠标动力学模型的用户身份认证与监控", 《西安交通大学学报》, vol. 42, no. 10, 31 October 2008 (2008-10-31) * |
| 王淼等: "行为截获技术对鼠标动力学身份认证的影响", 《微电子学与计算机》, vol. 30, no. 4, 30 April 2013 (2013-04-30) * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281795B (en) * | 2014-09-25 | 2017-10-31 | 同济大学 | Password fault-tolerance approach based on mouse behavior |
| CN104318435A (en) * | 2014-09-25 | 2015-01-28 | 同济大学 | Immunization method for user behavior detection in electronic transaction process |
| WO2016045225A1 (en) * | 2014-09-25 | 2016-03-31 | 同济大学 | Password fault tolerance method based on mouse behaviour |
| WO2016045514A1 (en) * | 2014-09-25 | 2016-03-31 | 同济大学 | Immunisation method for user behaviour model detection in electronic transaction process |
| CN104281795A (en) * | 2014-09-25 | 2015-01-14 | 同济大学 | Mouse action based password fault tolerance method |
| CN104881594A (en) * | 2015-05-06 | 2015-09-02 | 镇江乐游网络科技有限公司 | Smartphone ownership detection method based on accurate figure |
| CN104881594B (en) * | 2015-05-06 | 2018-04-03 | 镇江乐游网络科技有限公司 | It is a kind of based on the smart mobile phone ownership detection method precisely drawn a portrait |
| CN106817342A (en) * | 2015-11-30 | 2017-06-09 | 北京计算机技术及应用研究所 | Active identity authorization system based on user behavior feature recognition |
| CN105976201A (en) * | 2016-04-28 | 2016-09-28 | 北京小米移动软件有限公司 | Purchase behavior monitoring method for electronic business system and device |
| CN106156362A (en) * | 2016-08-01 | 2016-11-23 | 陈包容 | A kind of method and device automatically providing solution for early warning |
| CN106339316B (en) * | 2016-08-24 | 2019-01-11 | 上海爱企网络科技有限公司 | A kind of method and device that code segment is diagnosed in e-commerce platform |
| CN106339316A (en) * | 2016-08-24 | 2017-01-18 | 上海爱企网络科技有限公司 | Method and device for diagnosing code segment in e-commerce platform |
| CN106384027A (en) * | 2016-09-05 | 2017-02-08 | 四川长虹电器股份有限公司 | User identity recognition system and recognition method thereof |
| CN107122641A (en) * | 2017-04-25 | 2017-09-01 | 杭州安石信息技术有限公司 | Smart machine owner recognition methods and owner's identifying device based on use habit |
| CN107122641B (en) * | 2017-04-25 | 2020-06-16 | 杭州义盾信息技术有限公司 | Intelligent equipment owner identification method and intelligent equipment owner identification device based on use habit |
| CN107335220A (en) * | 2017-06-06 | 2017-11-10 | 广州华多网络科技有限公司 | A kind of recognition methods of passive user, device and server |
| CN107395562A (en) * | 2017-06-14 | 2017-11-24 | 广东网金控股股份有限公司 | A kind of financial terminal security protection method and system based on clustering algorithm |
| CN107908300A (en) * | 2017-11-17 | 2018-04-13 | 哈尔滨工业大学（威海） | A kind of synthesis of user's mouse behavior and analogy method and system |
| CN107908300B (en) * | 2017-11-17 | 2019-08-13 | 哈尔滨工业大学（威海） | A kind of synthesis of user's mouse behavior and analogy method and system |
| CN109407947A (en) * | 2018-09-30 | 2019-03-01 | 北京金山云网络技术有限公司 | Interface alternation and its verification method, logging request generation and verification method and device |
| CN111917801A (en) * | 2020-08-18 | 2020-11-10 | 南京工业大学浦江学院 | Petri network-based user behavior authentication method in private cloud environment |
| CN113569656A (en) * | 2021-07-02 | 2021-10-29 | 广州大学 | Examination room monitoring method based on deep learning |
| CN113569656B (en) * | 2021-07-02 | 2023-08-29 | 广州大学 | Examination room monitoring method based on deep learning |
| CN117194202A (en) * | 2023-11-08 | 2023-12-08 | 北京网藤科技有限公司 | System and method for detecting user operation dilemma based on webpage mouse behaviors |
| CN117194202B (en) * | 2023-11-08 | 2024-01-02 | 北京网藤科技有限公司 | System and method for detecting user operation dilemma based on webpage mouse behaviors |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103699822B (en) | 2016-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103699822B (en) | User's anomaly detection method in ecommerce based on mouse behavior | |
| Shi et al. | Detecting malicious social bots based on clickstream sequences | |
| Lee et al. | Uncovering social spammers: social honeypots+ machine learning | |
| Li et al. | TTAGN: Temporal transaction aggregation graph network for ethereum phishing scams detection | |
| US9396331B2 (en) | Systems and methods for security management based on cursor events | |
| CN103218355B (en) | A kind of method and apparatus generating label for user | |
| CN102970289B (en) | The identity identifying method of sing on web user behavior pattern | |
| CN103297469A (en) | Method and device of collecting website data | |
| WO2017084205A1 (en) | Network user identity authentication method and system | |
| CN102999572A (en) | User behavior mode digging system and user behavior mode digging method | |
| CN106878397A (en) | A kind of WEB user behaviors feedback method and system | |
| CN102904800A (en) | Method and system for sharing network transaction information with instant messaging contact person | |
| Selvakumar et al. | Enhanced K-means clustering algorithm for evolving user groups | |
| CN102314423A (en) | Method and device for detecting heat degree of subset in open type interactive platform | |
| CN103488947A (en) | Method and device for identifying instant messaging client-side account number stealing Trojan horse program | |
| EP3441892A1 (en) | Advertisement generating method, computer-readable storage medium and system | |
| Jin et al. | Filtering spam in Weibo using ensemble imbalanced classification and knowledge expansion | |
| CN102315978A (en) | Method and device for detecting abnormal conditions of subset in open-type interactive platform | |
| CN106874495A (en) | Based on the method that structure of web page is extracted in machine learning modeling | |
| CN106126538B (en) | Page conversion processing method and device | |
| Sadeghpour et al. | Poster: ReMouse Dataset: Measuring Similarity of Human-Generated Trajectories as an Important Step in Dealing with Session-Replay Bots | |
| CN114036511A (en) | Method and device for detecting script cheating on terminal based on privacy protection | |
| CN106789424A (en) | Server liveness detecting system and method | |
| CN102542031A (en) | Method, client and system for network link collection in instant messaging | |
| CN104850606A (en) | Method for summarizing social events in mobile crowd sensing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |