B
Bimal Viswanath
Researcher at Virginia Tech
Publications - 42
Citations - 5203
Bimal Viswanath is an academic researcher from Virginia Tech. The author has contributed to research in topics: Social network & Computer science. The author has an hindex of 18, co-authored 38 publications receiving 4227 citations. Previous affiliations of Bimal Viswanath include Max Planck Society & University of California, Santa Barbara.
Papers
More filters
Proceedings ArticleDOI
On the evolution of user interaction in Facebook
TL;DR: It is found that links in the activity network tend to come and go rapidly over time, and the strength of ties exhibits a general decreasing trend of activity as the social network link ages.
Proceedings ArticleDOI
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
TL;DR: This work presents the first robust and generalizable detection and mitigation system for DNN backdoor attacks, and identifies multiple mitigation techniques via input filters, neuron pruning and unlearning.
Proceedings ArticleDOI
You are who you know: inferring user profiles in online social networks
TL;DR: It is found that users with common attributes are more likely to be friends and often form dense communities, and a method of inferring user attributes that is inspired by previous approaches to detecting communities in social networks is proposed.
Proceedings ArticleDOI
Understanding and combating link farming in the twitter social network
Saptarshi Ghosh,Bimal Viswanath,Farshad Kooti,Naveen Kumar Sharma,Gautam Korlam,Fabrício Benevenuto,Niloy Ganguly,Krishna P. Gummadi +7 more
TL;DR: It is shown that a simple user ranking scheme that penalizes users for connecting to spammers can effectively address the link farming problem in Twitter by disincentivizing users from linking with other users simply to gain influence.
Proceedings ArticleDOI
An analysis of social network-based Sybil defenses
TL;DR: It is demonstrated that networks with well-defined community structure are inherently more vulnerable to Sybil attacks, and that, in such networks, Sybils can carefully target their links in order to make their attacks more effective.