most citedSoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

14 citations · 14 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025

From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization

Farah Wahida, M. A. P. Chamikara, Yashothara Shanmugarasa +3

Biometric systems, such as face recognition systems powered by deep neural networks (DNNs), rely on large and highly sensitive datasets. Backdoor attacks can subvert these systems…