CN108268762A - The mobile social networking user identity of Behavior-based control modeling knows fake method - Google Patents
The mobile social networking user identity of Behavior-based control modeling knows fake method Download PDFInfo
- Publication number
- CN108268762A CN108268762A CN201810043919.7A CN201810043919A CN108268762A CN 108268762 A CN108268762 A CN 108268762A CN 201810043919 A CN201810043919 A CN 201810043919A CN 108268762 A CN108268762 A CN 108268762A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- value
- identity
- true
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000006855 networking Effects 0.000 title abstract description 12
- 238000012549 training Methods 0.000 claims description 9
- 238000011160 research Methods 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000013459 approach Methods 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 34
- 230000003542 behavioural effect Effects 0.000 description 6
- 230000000295 complement effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 206010068052 Mosaicism Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000003765 sex chromosome Anatomy 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The mobile social networking user identity of present invention research Behavior-based control modeling knows fake method.So as to unanimously judge user behavior, the legitimacy of user is judged with this.The mobile social networking user identity of Behavior-based control modeling knows fake method, have benefited from the abundant information data that current mobile social networking provides, we get a large number of users social data, including position, Move Mode, social networks, user-generated content and shopping record etc..Using multivariate data as research object, the feature of these information is extracted.Using mixing Density Estimator, LDA text modelings the methods of realize to user behavior following three dimensions modeling:(1) geographical location (2) user generates text (3) social networks, the interception rate of detection is gone out by analog subscriber identity theft experimental calculation and bothers rate and precision ratio, thus evaluation system performance, the disadvantage of traditional identity identifying system is solved, the solution for information age safety problem provides new approaches and analysis method.
Description
Technical field
The present invention relates to mobile social networking user identity to know fake method.
Background technology
While the Internet, applications obtain universal, information security issue is also more and more prominent, and attacker can attempt to steal
User account steals individual privacy information or even malicious attack server.To ensure user security, traditional identification side
Method is easily stolen under the network attack to increasingly sharpen, therefore only can not meet reality by the system of simple user name password
Border needs.
In today that internet intelligent chemical conversion is development trend, the identity sensitive information of user will be made by extensive acquisition
With how to ensure the information security of user becomes a problem urgently to be resolved hurrily.In contrast, it is used to have behavioural characteristic with user
As the foundation of identification, there is uniqueness, non-reproduction and non repudiation, as long as method is designed
When just with very high accuracy, and independent of other ancillary equipments, will not being generated to the normal use of user dry
It disturbs, it is only necessary to the certification to user identity can be realized in the form of plug-in unit, and in real time, accurately user identity can be stolen
With being monitored.The user identity of Behavior-based control anomaly is known pseudo problem and is provided newly for mobile Internet information security issue
Visual angle, using the magnanimity information generated in mobile social networking, consider user behavior in physics-network-social space
Feature can obtain the daily geographical location of user according to user's record of registering using Density Estimator modeling user place of registering
Distributed model;User interest profile is extracted using text modeling mode widely applied in data mining, mark can be used as to use
A kind of behavioral data of family identity;User social contact preference pattern etc. is established using user social contact relationship.
The significant challenge that the modeling of mobile social networking user behavior often faces is Sparse sex chromosome mosaicism.Due to various
Condition limits, and the collection of user's specific behavior is recorded often than sparse, this is to influence user behavior modeling accuracy
Key factor.We intend by be based on user behavior projection (behavior of the user in different behavior subspaces) complementary effect come
The space-time cavity of behavioral data is filled up, with the modeling of this complete user behavior.
For this purpose, the mobile social networking user identity of present invention research Behavior-based control modeling knows fake method.So as to user
Behavior is unanimously judged, the legitimacy of user is judged with this.
Invention content
Have benefited from the abundant information data that current mobile social networking provides, we can get a large number of users social activity number
According to including position, Move Mode, social networks, user-generated content and shopping record etc..Using multivariate data as research object,
Extract the feature of these information.It is realized using the methods of mixing Density Estimator, LDA text modelings to user behavior following three
The modeling of a dimension:(1) geographical location (2) user generates text (3) social networks, is tested and counted by analog subscriber identity theft
It calculates the interception rate of detection and bothers rate and precision ratio, and thus carry out evaluation system performance, design is a kind of to be based on anomaly
Mobile social networking user behavior identity know fake method, solve traditional identity identifying system disadvantage, for the information age pacify
The solution of full problem provides new thinking and analysis method.
The invention reside in overcome the deficiencies in the prior art, for analyze user behavior in expected model threshold value it is consistent
Property, study the problem of user account is with the presence or absence of exception in mobile social networking.
For this purpose, the technical solution provided is:
A kind of user identity of Behavior-based control modeling knows pseudo Algorithm, which is characterized in that process is as follows:
Input:Information of registering, text message and the social networks of user's generation
Output:The true value of user identity
(1) it is registered in (check-in) geographical location information, the user text that action space is sent out on line according to user
Appearance and social networks of the user in entire social networks calculate Characteristic Distribution of the user's history data in three dimensionsAndPerform step (2).
(2) for the newly-generated behavior record of user, it is assessed in three dimensions:(1) data of newly registering are calculated
Probability density value logarithmic average(2) the theme probability distribution of newly-generated text is calculated(3) the social pass of new foundation is calculated
The interest distribution of systemPerform step (3).
(3) in information dimension of registering, by calculatingValue with by training, obtain can be by geographical position
Put the probability density logarithmic average threshold value S for distinguishing the user identity true and falsecIt is compared, if more than threshold value, then returns to UC=true,
Otherwise U is returnedC=false performs step (4).
(4) in text message dimension, for user's history Data subject probability distributionWith the master of the newly-generated text of user
Inscribe probability distributionCalculate the Jensen-Shannon divergences of two probability distributionBy its value and pass through training
The threshold value D of JS divergences between two obtained probability distributionTIt is compared, if less than threshold value, returns to UT=true, is otherwise returned
Return UT=false performs step (5).
(5) in social networks dimension, the text that interest can be expressed in friend's information is extracted according to the social networks of user
Information similarly calculates user friend's historical data theme probability distributionWith the theme probability distribution of the newly-generated text of user
And JS divergencesBy its value and threshold value DFIt is compared, if less than threshold value, returns to UT=true, is otherwise returned
Return UT=false performs step (6).
(6) the judgement U for user identity true value returned according to above (3) (4) (5)C,UT,UF, by three dimensions pair
The judgement of the user identity true and false takes union to obtain the final judge value U of user identityI=g (UC,UT,UF)。
The social network user Behavior law of position is primarily based on, user is being established just in multiple dimensions using valid data collection
Normal behavior model carries out Feature Selection, determines abnormal behaviour threshold value, and pass through its accuracy of experimental verification and validity.Then
Based on the research that early period models user behavior feature extraction and normal behaviour, behavior under bonding wire, on line behavior with it is social
Feature of the behavioural analysis user in cyberspace, considers the relevance of user behavior blended space, and design utilizes multiple
The user identity that the complementary effect of dimension is realized knows fake method and system.
The present invention it was proved that, this method is in accuracy rate and calculates better than previous research on the time.
Description of the drawings
The present invention is based on the mobile Internet user identity knowledge fake method system construction drawings of behavior modeling by Fig. 1
Fig. 2 inventive algorithm flow charts
Specific embodiment
(case)
The mobile Internet user identity of Behavior-based control modeling knows fake method system construction drawing, as shown in Figure 1.Entire scheme
It is divided into three phases:
First stage establishes user's off-line model for historical data, is responsible for the collection and processing of user's history data, raw
Into the regularity of distribution of the user behavior feature of corresponding dimension;(belonging to this field routine techniques)
Second stage be it is online collect the behavior record generation current signature stage, be responsible for the collection of user's current data with
The regularity of distribution of the behavioural characteristic of corresponding dimension is calculated in processing;(belonging to this field routine techniques)
Three phases know the pseudo- stage for user identity, are responsible for the data characteristics delivered according to the stage one and two, pass throughIt is more Dimension mergesProvide the judgement to user identity.
First stage specific implementation step:
Step 1-1, pre-processes user data, screens the validated user of each dimension.Three effective items of dimension
Part is respectively:User's history, which registers to record, will at least 5 times or more records of registering;User's text that action space is sent out on line
Content must enough fully can train to obtain the theme probability distribution of user's history data, that is, protect after removing stop-word
Demonstrate,prove the user of 200 or more effective words;The friend's number of user in the entire network will reach ten or more, based on this feature, note
The content of text of user friend is recorded, obtains the interest distribution of circle of friends in user's history data.
Step 1-2 registers data according to the history of user and the friend of user, using the method for Density Estimator (at this
Field has been the prior art) the probability density function f (x) of the position distribution that obtains registering.
Step 1-3, for the history text data of each user, accumulation is as a document, the textual data of whole users
According to just constituting a large-scale corpus.Model is generated by LDA document subject matters, user's history text data is established and is led
Model is inscribed, the corresponding theme probability distribution of every document is to form the theme probability distribution of the document user
For user social contact relation data, the text envelope of user friend's generation is obtained according to user social contact relationship by step 1-4
Breath similarly obtains the interest distribution of user friend's circle
Wherein:Above step 1-2,1-3 and 1-4 are to carry out side by side.
Second stage specific implementation step:
Step 2-1 for the data that user newly registers, substitutes into f (x) and obtains probability density, calculate its logarithmic average S=
1/n∑logf(x)。
Step 2-2 for the text data that user is newly-generated, passes through formulaIt can be calculated
The theme probability distribution of new textWord numbers of the wherein n (k) to belong to theme k in text, αkIt is that LDA training process obtains
The model parameter arrived.
Step 2-3 for the friend that user newly makes friends with, extracts the text data of new friend's generation, similarly can to new friend
The interest distribution of friend
Wherein:Above step 2-1,2-2 and 2-3 are to carry out side by side.
Phase III specific implementation step:
Step 3-1, the probability density logarithm for obtaining to distinguish the user identity true and false by geographical location by training are equal
It is worth threshold value Sc;Obtain to distinguish the Jensen- of two probability distribution of the user identity true and false by text message by training
The threshold value D of Shannon divergencesTAnd DF。
Step 3-2, for user version historical data theme probability distributionWith the theme probability of the newly-generated text of user
DistributionCalculate the JS divergences of two probability distribution
Step 3-3 is distributed user social contact relationship historical data interest probabilitiesWith the interest probabilities of the new friend of user
DistributionCalculate the JS divergences of two probability distribution
Step 3-4, for all mobile interchange network users, each feature being calculated according to step 3-1,3-2 and 3-3
Value, respectively from three geographical location, text message and social networks dimensions according to corresponding judgment criteria Sc、DTAnd DFIt gives
Go out the judgement U of user identityC,UT,UF, three dimensions are merged to obtain user identity to the judgement of the user identity true and false
Final judge value UI=g (UC,UT,UF)。
Algorithm
The user identity of Behavior-based control modeling knows pseudo Algorithm (idiographic flow is shown in Fig. 2)
Input:Information of registering, text message and the social networks of user's generation
Output:The true value of user identity
(1) it is registered in (check-in) geographical location information, the user text that action space is sent out on line according to user
Appearance and social networks of the user in entire social networks calculate Characteristic Distribution of the user's history data in three dimensionsAndPerform step (2).
(2) for the newly-generated behavior record of user, it is assessed in three dimensions:(1) data of newly registering are calculated
Probability density value logarithmic average(2) the theme probability distribution of newly-generated text is calculated(3) the social pass of new foundation is calculated
The interest distribution of systemPerform step (3).
(3) in information dimension of registering, by calculatingValue with by training, obtain can be by geographical position
Put the probability density logarithmic average threshold value S for distinguishing the user identity true and falsecIt is compared, if more than threshold value, then returns to UC=true,
Otherwise U is returnedC=false performs step (4).
(4) in text message dimension, for user's history Data subject probability distributionWith the master of the newly-generated text of user
Inscribe probability distributionCalculate the Jensen-Shannon divergences of two probability distributionBy its value and pass through training
The threshold value D of JS divergences between two obtained probability distributionTIt is compared, if less than threshold value, returns to UT=true, is otherwise returned
Return UT=false performs step (5).
(5) in social networks dimension, the text that interest can be expressed in friend's information is extracted according to the social networks of user
Information similarly calculates user friend's historical data theme probability distributionWith the theme probability distribution of the newly-generated text of user
And JS divergencesBy its value and threshold value DFIt is compared, if less than threshold value, returns to UT=true, is otherwise returned
Return UT=false performs step (6).
(6) the judgement U for user identity true value returned according to above (3) (4) (5)C,UT,UF, by three dimensions pair
The judgement of the user identity true and false takes union to obtain the final judge value U of user identityI=g (UC,UT,UF)。
It was proved that this method is in accuracy rate and calculates research better than previous on the time.
1 this item purpose innovative point
1. by user's historical behavior data, user's normal behaviour model is established.
2. using the complementary effect of multiple dimension behaviors, more accurate identity is obtained and has known fake method.
3. the previous identity of difference knows pseudo- mode, independent of hardware device, according to the behavioural characteristic conduct of user itself
A kind of mark of user identity, and with very high confidence level.
Annotation:Related term in the present invention and following data can be found in for previous major technique.
[1]Bao J,Zheng Y,Wilkie D,et al.A survey on recommendations in
location-based social networks[J].ACM Transaction on Intelligent Systems and
Technology,2013.
[2]David M.Blei,Andrew Y.Ng,Michael I.Jordan.Latent Dirichlet
Allocation[J].//Journal of machine learning research,2003,993-1022
[3]Wang X,Mccallum A,Wei X.Topical N-Grams:Phrase And Topic
Discovery,With An Application To Information Retrieval[C]//Data Mining,
2007.ICDM 2007.Seventh IEEE International Conference on.2007:697–702
[4]Jie Bao,Yu Zheng,Mohamed F.Mokbel.Location-based and preference-
aware recommendation using sparse geo-social networking data.[J]//
International Conference on Advances in Geographic Information Systems,ACM,
2012
[5]Lichman M,Smyth P.Modeling human location data with mixtures of
kernel densities[C]//Proceedings of the 20th ACM SIGKDD international
conference on Knowledge discovery and data mining.ACM,2014:35-44.
[6]Cho E,Myers S A,Leskovec J.Friendship and mobility:user movement
in location-based social networks[C]//Proceedings of the 17th ACM SIGKDD
international conference on Knowledge discovery and data mining.ACM,2011:
1082-1090.
[7] Yang Song, Zheng Hu, Xiaoming Leng.Friendship influence on mobile
behavior of location based social network users.[J]//Journal of
Communications and Networks,2015.
Claims (1)
1. a kind of user identity of Behavior-based control modeling knows pseudo Algorithm, which is characterized in that process is as follows:
Input:Information of registering, text message and the social networks of user's generation
Output:The true value of user identity
(1) according to user register (check-in) geographical location information, the user content of text that action space is sent out on line and
Social networks of the user in entire social networks calculate Characteristic Distribution of the user's history data in three dimensionsAndPerform step (2).
(2) for the newly-generated behavior record of user, it is assessed in three dimensions:(1) the general of data of newly registering is calculated
The logarithmic average of rate density value(2) the theme probability distribution of newly-generated text is calculated(3) it calculates and newly establishes social networks
Interest is distributedPerform step (3).
(3) in information dimension of registering, by calculatingValue with by training, obtain can be by geographical location area
Divide the probability density logarithmic average threshold value S of the user identity true and falsecIt is compared, if more than threshold value, then returns to UC=true, otherwise
Return to UC=false performs step (4).
(4) in text message dimension, for user's history Data subject probability distributionIt is general with the theme of the newly-generated text of user
Rate is distributedCalculate the Jensen-Shannon divergences of two probability distributionBy its value with being obtained by training
Two probability distribution between JS divergences threshold value DTIt is compared, if less than threshold value, returns to UT=true, otherwise returns to UT
=false performs step (5).
(5) in social networks dimension, the text message that interest can be expressed in friend's information is extracted according to the social networks of user,
Similarly calculate user friend's historical data theme probability distributionWith the theme probability distribution of the newly-generated text of userAnd JS
DivergenceBy its value and threshold value DFIt is compared, if less than threshold value, returns to UT=true, otherwise returns to UT=
False performs step (6).
(6) the judgement U for user identity true value returned according to above (3) (4) (5)C,UT,UF, by three dimensions to user
The judgement of the identity true and false takes union to obtain the final judge value U of user identityI=g (UC,UT,UF)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810043919.7A CN108268762B (en) | 2018-01-17 | 2018-01-17 | Mobile social network user identity identification method based on behavior modeling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810043919.7A CN108268762B (en) | 2018-01-17 | 2018-01-17 | Mobile social network user identity identification method based on behavior modeling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108268762A true CN108268762A (en) | 2018-07-10 |
CN108268762B CN108268762B (en) | 2021-04-30 |
Family
ID=62775799
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810043919.7A Active CN108268762B (en) | 2018-01-17 | 2018-01-17 | Mobile social network user identity identification method based on behavior modeling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108268762B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598110A (en) * | 2018-12-10 | 2019-04-09 | 北京羽扇智信息科技有限公司 | A kind of recognition methods of user identity and device |
CN111475738A (en) * | 2020-05-22 | 2020-07-31 | 哈尔滨工程大学 | Heterogeneous social network location anchor link identification method based on meta-path |
CN116260715A (en) * | 2023-05-09 | 2023-06-13 | 广东卓柏信息科技有限公司 | Account safety early warning method, device, medium and computing equipment based on big data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103853841A (en) * | 2014-03-19 | 2014-06-11 | 北京邮电大学 | Method for analyzing abnormal behavior of user in social networking site |
US20150264079A1 (en) * | 2013-03-06 | 2015-09-17 | Facebook, Inc. | Detection of lockstep behavior |
CN106202488A (en) * | 2016-07-19 | 2016-12-07 | 西北工业大学 | Estimation user is to the method for physical event distance |
CN106600052A (en) * | 2016-12-12 | 2017-04-26 | 西安交通大学 | User attribute and social network detection system based on space-time locus |
-
2018
- 2018-01-17 CN CN201810043919.7A patent/CN108268762B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150264079A1 (en) * | 2013-03-06 | 2015-09-17 | Facebook, Inc. | Detection of lockstep behavior |
CN103853841A (en) * | 2014-03-19 | 2014-06-11 | 北京邮电大学 | Method for analyzing abnormal behavior of user in social networking site |
CN106202488A (en) * | 2016-07-19 | 2016-12-07 | 西北工业大学 | Estimation user is to the method for physical event distance |
CN106600052A (en) * | 2016-12-12 | 2017-04-26 | 西安交通大学 | User attribute and social network detection system based on space-time locus |
Non-Patent Citations (1)
Title |
---|
郭昊: "基于位置社交网络的用户行为建模与研究", 《中国优秀硕士学位论文全文数据库(电子期刊)》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109598110A (en) * | 2018-12-10 | 2019-04-09 | 北京羽扇智信息科技有限公司 | A kind of recognition methods of user identity and device |
CN111475738A (en) * | 2020-05-22 | 2020-07-31 | 哈尔滨工程大学 | Heterogeneous social network location anchor link identification method based on meta-path |
CN111475738B (en) * | 2020-05-22 | 2022-05-17 | 哈尔滨工程大学 | Heterogeneous social network location anchor link identification method based on meta-path |
CN116260715A (en) * | 2023-05-09 | 2023-06-13 | 广东卓柏信息科技有限公司 | Account safety early warning method, device, medium and computing equipment based on big data |
CN116260715B (en) * | 2023-05-09 | 2023-09-01 | 国品优选(北京)品牌管理有限公司 | Account safety early warning method, device, medium and computing equipment based on big data |
Also Published As
Publication number | Publication date |
---|---|
CN108268762B (en) | 2021-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dahal et al. | Topic modeling and sentiment analysis of global climate change tweets | |
Zannettou et al. | On the origins of memes by means of fringe web communities | |
Hou et al. | Survey on data analysis in social media: A practical application aspect | |
Steiger et al. | Twitter as an indicator for whereabouts of people? Correlating Twitter with UK census data | |
Nakano et al. | Analysis of cyber aggression and cyber-bullying in social networking | |
CN103324636B (en) | The system and method for commending friends in social networks | |
CN103970752B (en) | Independent access person's quantity survey (surveying) method and system | |
CN106027577A (en) | Exception access behavior detection method and device | |
Wang et al. | Confidence-aware truth estimation in social sensing applications | |
Korayem et al. | De-anonymizing users across heterogeneous social computing platforms | |
CN106874253A (en) | Recognize the method and device of sensitive information | |
CN108268762A (en) | The mobile social networking user identity of Behavior-based control modeling knows fake method | |
CN104166726A (en) | Microblog text stream oriented sudden keyword detecting method | |
CN110134876A (en) | A kind of cyberspace Mass disturbance perception and detection method based on gunz sensor | |
Sun et al. | Efficient event detection in social media data streams | |
Shi et al. | Rumor detection of COVID-19 pandemic on online social networks | |
Wang et al. | Fusing behavioral projection models for identity theft detection in online social networks | |
Elyusufi et al. | Social networks fake profiles detection based on account setting and activity | |
Murakami et al. | Privacy-preserving multiple tensor factorization for synthesizing large-scale location traces with cluster-specific features | |
Qian et al. | Social network de-anonymization: More adversarial knowledge, more users re-identified? | |
WO2022028131A1 (en) | Data processing model acquisition method and apparatus based on privacy protection, terminal device, and storage medium | |
Sun et al. | Anomaly subgraph detection with feature transfer | |
Ajesh et al. | A hybrid method for fake profile detection in social networkusing artificial intelligence | |
Wang et al. | Co-location social networks: Linking the physical world and cyberspace | |
CN116383786B (en) | Big data information supervision system and method based on Internet of things |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |