5 papers
Chameleon: Robust Defense Against Tor Website Fingerprinting via Many-to-Many Traffic Morphing
Yuwen Cui, Kai Wei, Kehan Shen +4
Website fingerprinting (WF) attacks can infer users' browsing activities from encrypted Tor traffic by exploiting side-channel features. Although many WF defenses have been propose…
Which Source Wins? Task-Dependent Reliance in Vision-Language Models
Rodela Ghosh, Aviral Gupta, Guangjing Wang
Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harder to read, it is unclear how a model shifts its reliance between them. We stud…
One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models
Sudharshan Balaji, Yili Ren, Guangjing Wang +2
Machine unlearning is widely used to remove hazardous knowledge from large language models. Modern Vision-Language Models (VLMs), however, process both text and visual inputs, rais…
Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting
Alabi Mehzabin Anisha, Guangjing Wang, Sriram Chellappan
State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field's security ramifications, there is ac…
A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges
Yuwen Cui, Guangjing Wang, Khanh Vu +7
The Tor network provides users with strong anonymity by routing their internet traffic through multiple relays. While Tor encrypts traffic and hides IP addresses, it remains vulner…