36 Hits in 5.7 sec

Social Turing Tests: Crowdsourcing Sybil Detection [article]

Gang Wang, Manish Mohanlal, Christo Wilson, Xiao Wang, Miriam Metzger, Haitao Zheng, Ben Y. Zhao
2012 arXiv   pre-print
In this paper, we explore the feasibility of a crowdsourced Sybil detection system for OSNs.  ...  We use these results to drive the design of a multi-tier crowdsourcing Sybil detection system.  ...  We hope this will pave the way towards testing and deployment of crowdsourced Sybil detection systems by large social networks.  ... 
arXiv:1205.3856v2 fatcat:ieifn32onjf6daql5f735myzay

Sybil Attacks and Their Defenses in the Internet of Things

Kuan Zhang, Xiaohui Liang, Rongxing Lu, Xuemin Shen
2014 IEEE Internet of Things Journal  
We then present some Sybil defense schemes, including social graph-based Sybil detection (SGSD), behavior classification-based Sybil detection (BCSD), and mobile Sybil detection with the comprehensive  ...  Index Terms-Behavior classification, Internet of Things (IoT), mobile social network, social network, Sybil attack.  ...  They color the normal clusters that contain a seed sequence; otherwise, the uncolored clusters are Sybil ones. With crowdsourcing and social Turing tests, Wang et al.  ... 
doi:10.1109/jiot.2014.2344013 fatcat:lvq4u25hnzewnfvuf6nxqzu4oa

Survey of Sybil Attacks in Social Networks [article]

Rupesh Gunturu
2015 arXiv   pre-print
This paper reviews the Sybil attack in social networks, which has the potential to compromise the whole distributed network.  ...  In the Sybil attack, the malicious user claims multiple identities to compromise the network.  ...  In [52] , Wang et al, proposes a Sybil detection scheme based on crowd-sourcing and Social Turing test. Turing test is the ability of a machine to think intelligently similar to a human being.  ... 
arXiv:1504.05522v1 fatcat:ijqpjvrlivgqjm53k6ysyrs2wm

You Are How You Click: Clickstream Analysis for Sybil Detection

Gang Wang, Tristan Konolige, Christo Wilson, Xiao Wang, Haitao Zheng, Ben Y. Zhao
2013 USENIX Security Symposium  
We validate our clickstream models using ground-truth traces of 16,000 real and Sybil users from Renren, a large Chinese social network with 220M users.  ...  Finally, we worked with collaborators at Renren and LinkedIn to test our prototype on their server-side data.  ...  Online Turing tests such as CAPTCHAs are routinely solved by dedicated workers for pennies per request [22] , and even complex humanbased tasks can be overcome by a growing community of malicious crowdsourcing  ... 
dblp:conf/uss/WangKWWZZ13 fatcat:2nzz5lsqjveh5d32vns5hnq3de

Exploiting mobile social behaviors for Sybil detection

Kuan Zhang, Xiaohui Liang, Rongxing Lu, Kan Yang, Xuemin Sherman Shen
2015 2015 IEEE Conference on Computer Communications (INFOCOM)  
In this paper, we propose a Social-based Mobile Sybil Detection (SMSD) scheme to detect Sybil attackers from their abnormal contacts and pseudonym changing behaviors.  ...  In addition, investigating mobile user's contact distribution and social proximity, we propose a semi-supervised learning with Hidden Markov Model to detect the colluded mobile users.  ...  [15] exploit crowdsourcing and social Turing tests for a distributed Sybil detection scheme.  ... 
doi:10.1109/infocom.2015.7218391 dblp:conf/infocom/ZhangLLYS15 fatcat:wdppvdscjfgmvgzgnxfuktvdxm

Social Bots Detection via Fusing BERT and Graph Convolutional Networks

Qinglang Guo, Haiyong Xie, Yangyang Li, Wen Ma, Chao Zhang
2021 Symmetry  
Social robot detection uses supervised classification based on artificial feature extraction.  ...  The experiment shows that a better performance can also be achieved by BGSRD on a wide range of social robot detection datasets.  ...  Crowdsourcing Social Machine Account Detection Platform Reference [11] proposes a crowdsourcing social machine account detection platform.  ... 
doi:10.3390/sym14010030 fatcat:zqeq32txhfa3jhr6nsv3cwfdd4

Strength in Numbers

Bimal Viswanath, Muhammad Ahmad Bashir, Muhammad Bilal Zafar, Simon Bouget, Saikat Guha, Krishna P. Gummadi, Aniket Kate, Alan Mislove
2015 Proceedings of the 2015 ACM on Conference on Online Social Networks - COSN '15  
Existing defenses that largely focus on detecting individual Sybil identities have a fundamental limitation: Adaptive attackers can create hard-to-detect Sybil identities to tamper arbitrary crowd computations  ...  Popular social and e-commerce sites increasingly rely on crowd computing to rate and rank content, users, products and businesses.  ...  CONCLUSION In this paper, we tackle the challenging problem of detecting when computations on crowdsourcing systems like Twitter or Yelp have been tampered by fake (Sybil) identities.  ... 
doi:10.1145/2817946.2817964 dblp:conf/cosn/ViswanathBZBGGK15 fatcat:nkw7p4vkgvbetcshn6laepx4va

Session reports for SIGCOMM 2010

Shailesh Agrawal, Immanuel Ilavarasan Thomas, Arun Vishwanath, Tianyin Xu, Fang Yu, Kavitha Athota, Pramod Bhatotia, Piyush Goyal, Phani Krisha, Kirtika Ruchandan, Nishanth Sastry, Gurmeet Singh (+1 others)
2011 Computer communication review  
Hypothesis -community structure makes identifying sybils harder. Testing community structure hypothesis: 8 real world networks. Simulated attack by consistently adding sybils.  ...  Session 11: Social Networks Report by Nishanth Sastry, Cambridge ( and Gurmeet Singh, IIT Guwahati ( An Analysis of Social Network-Based Sybil Defenses  ... 
doi:10.1145/1925861.1925873 fatcat:jpaoo55h75hprb5k2vlkin5zzi

Beyond AMT: An Analysis of Crowd Work Platforms [article]

Donna Vakharia, Matthew Lease
2013 arXiv   pre-print
Systems CrowdFlower CrowdSource MobileWorks oDesk Distinguishing Fea- tures • Whose Crowd?  ...  MobileWorks uses dynamic work routing, peer management, and social interaction techniques, with native workflow support for QA. oDesk uses testing, certifications, training, work history and feedback ratings  ...  on smart phones and tablets; support hierarchical organization; detect and prevent task starvation.  ... 
arXiv:1310.1672v1 fatcat:odg6c2ll7rd6fd2y5c7cw3dvt4

SoK: Applying Machine Learning in Security - A Survey [article]

Heju Jiang, Jasvir Nagra, Parvez Ahammad
2016 arXiv   pre-print
Consequently, research on applying and designing ML algorithms and systems for security has grown fast, ranging from intrusion detection systems(IDS) and malware classification to security policy management  ...  Defeating audio and visual CAPTCHAs(Completely Automated Public Turing test to tell Computers and Humans Apart) [67, 68, 68, 69, 70] , cracking passwords [71, 72, 73] , measuring password strengths  ...  Partly because there is already a 2013 SoK on evolution of Sybil defense [15] in online social networks(OSN), and partly because we would like to leave it as a small exercise to our readers, we excluded  ... 
arXiv:1611.03186v1 fatcat:hfvc5hhu7ze77lrnjufslcg6gm

AI Evaluation: past, present and future [article]

Jose Hernandez-Orallo
2016 arXiv   pre-print
We discuss several possibilities: the adaptation of cognitive tests used for humans and animals, the development of tests derived from algorithmic information theory or more general approaches under the  ...  Social Turing Tests: Crowdsourcing sybil detection. arXiv preprint arXiv:1205.3856, 2012. 6 [177] K. Warwick. Turing Test success marks milestone in computing history.  ...  Similarly, the detection of bots in social networks (sybils) and crowdsourcing platforms rely on tests that are variants of CAPTCHAs, the Turing Test, or the observation and analysis of user profiles and  ... 
arXiv:1408.6908v3 fatcat:6g5h2nzaezey5a3qy3us7lnkvu

Online Social Deception and Its Countermeasures for Trustworthy Cyberspace: A Survey [article]

Zhen Guo, Jin-Hee Cho, Ing-Ray Chen, Srijan Sengupta, Michin Hong, Tanushree Mitra
2020 arXiv   pre-print
attacks and cybercrimes; (iii) comprehensive defense mechanisms embracing prevention, detection, and response (or mitigation) against OSD attacks along with their pros and cons; (iv) datasets/metrics  ...  In this paper, we conducted an extensive survey, covering (i) the multidisciplinary concepts of social deception; (ii) types of OSD attacks and their unique characteristics compared to other social network  ...  The LCS curve from behavioral model is used to detect more sophisticated types of crowdsourcing spammers.  ... 
arXiv:2004.07678v1 fatcat:k4a6siywefb6lhkmyn67lmoqwe

Humanode Whitepaper: You are [not] a bot [article]

Dato Kavazi, Victor Smirnov, Sasha Shilina, MOZGIII, MingDong Li, Rafael Contreras, Hardik Gajera, Dmitry Lavrenov, the Humanode Core
2021 arXiv   pre-print
and sustainable financial network: 1) a bio-authorization module based on cryptographically secure neural networks for the private classification of 3D templates of users' faces 2) a private Liveness detection  ...  Sybil detection techniques based on the concept of graph random walk and mix time 2. Sybil tolerance techniques, which limit the effects of Sybil attack edges [93, 94] .  ...  Humanode uses various techniques for preventing Sybil attacks: Recurring Costs General This technique is a form of resource testing where resource tests are performed at regular time intervals to impose  ... 
arXiv:2111.13189v1 fatcat:6pc4nj46sjdkvketwydvwh2ulu

Twitter Spam Detection: A Systematic Review [article]

Sepideh Bazzaz Abkenar, Mostafa Haghi Kashani, Mohammad Akbari, Ebrahim Mahdipour
2020 arXiv   pre-print
Nowadays, with the rise of Internet access and mobile devices around the globe, more people are using social networks for collaboration and receiving real-time information.  ...  This review focuses on comparing the existing research techniques on Twitter spam detection systematically.  ...  Leveraging crowdsourcing techniques, such as Amazon Turk, is a common approach in social science to mitigate this problem, it yet is insufficient.  ... 
arXiv:2011.14754v2 fatcat:byldhhoffbhhldsxdj7siybsua

Social Media and Microblogs Credibility: Identification, Theory Driven Framework, and Recommendation

Khubaib Ahmed Qureshi, Rauf Ahmed Shams Malick, Muhammad Sabih
2021 IEEE Access  
Social media microblogs are extensively used to get news and other information. It brings the real challenge to distinguish that what particular information is credible.  ...  The framework is generic to social media and specifically implemented for microblogs. It is completely transformed up to features level, in the context of microblogs.  ...  There are studies found for such malicious profiles identification and detection, for example Bot/ Trolls/ Cyborg/ Sybils/ Content Polluters/ Social Spambots and its detection: [23] , [26] , [98] -  ... 
doi:10.1109/access.2021.3114417 fatcat:nawg5fgd55fyxcriho3urlxwoq
« Previous Showing results 1 — 15 out of 36 results