3 papers
cs.LG2025
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
Tao Sun, Lu Pang, Weimin Lyu +2
Deep neural networks are vulnerable to backdoor attacks, where an adversary manipulates the model behavior through overlaying images with special triggers. Existing backdoor defens…
cs.CV2025
Backdooring Vision-Language Models with Out-Of-Distribution Data
Weimin Lyu, Jiachen Yao, Saumya Gupta +6
The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descr…
cs.CR2024
Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations
Lu Pang, Tao Sun, Weimin Lyu +2
Recently, backdoor attack has become an increasing security threat to deep neural networks and drawn the attention of researchers. Backdoor attacks exploit vulnerabilities in third…