108 Hits in 4.9 sec

Improving Sybil Detection via Graph Pruning and Regularization Techniques

Huanhuan Zhang, Jie Zhang, Carol J. Fung, Chang Xu
2015 Asian Conference on Machine Learning  
Specifically, we first propose an effective graph pruning technique to enhance the robustness of existing Sybil defense mechanisms against target attacks, by utilizing the local structural similarity between  ...  Experimental results on four popular online social network datasets demonstrate that our proposed techniques can significantly improve the detection accuracy over the original Sybil defense mechanisms.  ...  Effectiveness against Random Attacks We have shown that our proposed graph pruning and regularization techniques can significantly improve Sybil detection accuracy under target attacks.  ... 
dblp:conf/acml/ZhangZFX15 fatcat:jofy4vqeq5ardak26vzaypmuaq

Combating Friend Spam Using Social Rejections

Qiang Cao, Michael Sirivianos, Xiaowei Yang, Kamesh Munagala
2015 2015 IEEE 35th International Conference on Distributed Computing Systems  
between Sybils and non-Sybil users.  ...  To efficiently obtain the graph cut, we extend the Kernighan-Lin heuristic and use it to iteratively detect and remove the accounts that send out friend spam.  ...  As a demonstration of Rejecto's effectiveness on improving OSN-related services, we apply it to social-graph-based Sybil detection.  ... 
doi:10.1109/icdcs.2015.32 dblp:conf/icdcs/CaoSYM15 fatcat:5j5zlt3fxvflxi2e7k7teoyrjq

Aiding the Detection of Fake Accounts in Large Scale Social Online Services

Qiang Cao, Michael Sirivianos, Xiaowei Yang, Tiago Pregueiro
2012 Symposium on Networked Systems Design and Implementation  
It relies on social graph properties to rank users according to their perceived likelihood of being fake (Sybils).  ...  OSN operators currently expend significant resources to detect, manually verify, and shut down fake accounts.  ...  This work was partly funded by NSF Awards CNS-0845858 and CNS-1017858.  ... 
dblp:conf/nsdi/CaoSYP12 fatcat:jpvvaht7r5eprgsyaw5k6cqn2a

Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks [article]

Haizhong Zheng, Minhui Xue, Hao Lu, Shuang Hao, Haojin Zhu, Xiaohui Liang, Keith Ross
2017 arXiv   pre-print
In this paper, we conduct the first study to define, characterize, and detect elite Sybil attacks.  ...  We design ElsieDet, a three-stage Sybil detection scheme, which first separates out suspicious groups of users, then identifies the campaign windows, and finally identifies elite Sybil users participating  ...  ACKNOWLEDGMENT This work was supported in part by the National Science Foundation of China, under Grants 71671114, 61672350, and U1405251. Corresponding author: Haojin Zhu.  ... 
arXiv:1709.06916v2 fatcat:su4mdo43gngnzgh2npkxxrnzdi

Unsupervised Clickstream Clustering for User Behavior Analysis

Gang Wang, Xinyi Zhang, Shiliang Tang, Haitao Zheng, Ben Y. Zhao
2016 Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems - CHI '16  
The partitioning process leverages iterative feature pruning to capture the natural hierarchy within user clusters and produce intuitive features for visualizing and understanding captured user behaviors  ...  In this paper, we build an unsupervised system to capture dominating user behaviors from clickstream data (traces of users' click events), and visualize the detected behaviors in an intuitive manner.  ...  This project was supported by NSF grants CNS-1527939 and IIS-1321083.  ... 
doi:10.1145/2858036.2858107 dblp:conf/chi/WangZTZZ16 fatcat:jxx7djf33fettcm2njlkappav4

Sybil defenses in mobile social networks

Wei Chang, Jie Wu, Chiu C. Tan, Feng Li
2013 2013 IEEE Global Communications Conference (GLOBECOM)  
First, our system is based on both trust and distrust relations. Second, instead of storing the entire social graph, users carry limited information related to themselves.  ...  Most social network-based Sybil defenses adopt the assumptions that the honest region is a fast-mixing network.  ...  Paper [7] proposed a strategy for detecting Sybils in mobile networks: each user locally stores a friendship graph and a foe graph.  ... 
doi:10.1109/glocom.2013.6831144 dblp:conf/globecom/ChangWTL13 fatcat:rh7peaubnvathhmbx3yqnff2fe

Sybil-Resilient Online Content Voting

Dinh Nguyen Tran, Bonan Min, Jinyang Li, Lakshminarayanan Subramanian
2009 Symposium on Networked Systems Design and Implementation  
However, any content voting system is susceptible to the Sybil attack where adversaries can out-vote real users by creating many Sybil identities.  ...  SumUp uses the technique of adaptive vote flow aggregation to limit the number of bogus votes cast by adversaries to no more than the number of attack edges in the trust network (with high probability)  ...  We are grateful to Krishna Gummadi (our shepard), Haifeng Yu, Aditya Dhananjay, Michael Paik, Eric Hielscher, and the anonymous reviewers whose comments have helped us improve the paper.  ... 
dblp:conf/nsdi/TranMLS09 fatcat:3lxyh4szfjd5vdinwopyu6zq3u

The Art of Social Bots: A Review and a Refined Taxonomy [article]

Majd Latah
2019 arXiv   pre-print
Our study can help OSN administrators and researchers understand the destructive potential of malicious social bots and can improve the current defence strategies against them.  ...  We also suggest a refined taxonomy of detection approaches from social network perspective, as well as commonly used datasets and their corresponding findings.  ...  Acknowledgement We would like to thank Gonca Gürsun and Huseyin Ulusoy for their fruitful comments on the manuscript, which helped us improve the quality of this work.  ... 
arXiv:1905.03240v1 fatcat:a4bliz7dpvgy5aacvodamlaata

Two Step Verification technique For Detection of Malicious Nodes in Wireless Sensor Networks

Mandeep Kumar
It is analyzed that two step verification technique detect malicious nodes successfully and it also leads to improve network performance in terms of Delay, PDR and Packetloss.  ...  The Sybil attack is the attack which is possible in wireless sensor networks and it affect network performance.  ...  The authors first utilized the similarity-based graph pruning through which the entire network is divided into non-Sybil and Sybil regions.  ... 
doi:10.26782/jmcms.2019.02.00032 fatcat:jexszxmsfrhu5a722mm4honm54

Implementing Truthful Routing Path Generation in WSN through TARF

Premakshi B.Dohe, Rajesh Shukla
2014 International Journal of Computer Applications  
To face this downside, we tend to propose a truthful routing protocol that adopts the routing principle to address the network dimensions, and depends on a distributed trust model for the detection and  ...  Associate in Nursing opposer will exploit this defect to launch numerous harmful or perhaps devastating attacks against the routing protocols, together with sink attacks, hollow attacks and Sybil attacks  ...  hard-to-detect attacks against routing, like selective forwarding, hollow attacks, sink attacks and Sybil attacks.  ... 
doi:10.5120/17453-8416 fatcat:2vxgxmwgyzcojnen4relij6w5i

Robust active attacks on social graphs

Sjouke Mauw, Yunior Ramírez-Cruz, Rolando Trujillo-Rasua
2019 Data mining and knowledge discovery  
patterns later used to re-identify the sybil nodes and other users after anonymisation.  ...  In order to prevent the disclosure of privacy-sensitive data, such as names and relations between users, social network graphs have to be anonymised before publication.  ...  The work reported in this paper received funding from Luxembourg's Fonds National de la Recherche (FNR), via Grant C17/IS/11685812 (PrivDA).  ... 
doi:10.1007/s10618-019-00631-5 fatcat:uiwc5ikddzeozjyhc5jcknggvq

Intrusion Detection Systems for IoT: opportunities and challenges offered by Edge Computing and Machine Learning [article]

Pietro Spadaccino, Francesca Cuomo
2022 arXiv   pre-print
Key components of current cybersecurity methods are the Intrusion Detection Systems (IDSs) were different techniques and architectures are applied to detect intrusions.  ...  We focus on anomaly-based IDSs, showing the main techniques that can be leveraged to detect anomalies and we present machine learning techniques and their application in the context of an IDS, describing  ...  They have also presented and categorized defense mechanisms into three main classes named Social Graph-based Sybil Detection (SGSD), Behavior Classification-based Sybil Detection (BCSD) and Mobile Sybil  ... 
arXiv:2012.01174v2 fatcat:f4ffzbgzuvhhdcv6hv4d2znnrm

Sneak into Devil's Colony- A study of Fake Profiles in Online Social Networks and the Cyber Law [article]

Mudasir Ahmad Wani, Suraiya Jabin, Ghulam Yazdani, Nehaluddin Ahmadd
2018 arXiv   pre-print
Furthermore, an attempt is made to present several machine learning techniques employed to design different fake profile detection systems.  ...  Daily reports of the security and privacy threats in the OSNs demand not only the intelligent automated detection systems that can identify and alleviate fake profiles in real time but also the reinforcement  ...  Based on the writing style of the users, the author pruned the graph to obtain sockpuppet network (SPN).  ... 
arXiv:1803.08810v1 fatcat:c6kqphdeyvfkfhho4lkoxl7zay

Evaluating Changes to Fake Account Verification Systems

Fedor Kozlov, Isabella Yuen, Jakub Kowalczyk, Daniel Bernhardt, David Freeman, Paul Pearce, Ivan Ivanov
2020 International Symposium on Recent Advances in Intrusion Detection  
Social networks employ sophisticated detection mechanisms based on machine-learning classifiers and graph analysis to identify and remediate the actions of fake accounts.  ...  In order to maintain a verification system's effectiveness over time, it is important to iterate on the system to improve the real user experience and adapt the platform's response to adversarial actions  ...  Graph-based and sybil detection focuses on exploring connections between identities and their properties inside social graph to detect fake accounts [9, 23, 56] .  ... 
dblp:conf/raid/KozlovYKBFPI20 fatcat:e52axyebjvgatlpi7ebobxbw5y

Measuring, Characterizing, and Detecting Facebook Like Farms [article]

Muhammad Ikram, Lucky Onwuzurike, Shehroze Farooqi, Emiliano De Cristofaro, Arik Friedman, Guillaume Jourjon, Dali Kaafar, M. Zubair Shafiq
2017 arXiv   pre-print
mimic regular users.  ...  Aiming to fill this gap, we present a honeypot-based comparative measurement study of page likes garnered via Facebook advertising and from popular like farms.  ...  to improve detection accuracy.  ... 
arXiv:1707.00190v2 fatcat:tebevt6grfbotmz5dznkuxr6si
« Previous Showing results 1 — 15 out of 108 results