3 papers
cs.CV2026
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…
cs.CV2026
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…
cs.CR2026
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…