2 papers
cs.CR2025
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Xiaoxing Mo, Yuxuan Cheng, Nan Sun +3
Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution…
cs.CV2022
Attention Distraction: Watermark Removal Through Continual Learning with Selective Forgetting
Qi Zhong, Leo Yu Zhang, Shengshan Hu +3
Fine-tuning attacks are effective in removing the embedded watermarks in deep learning models. However, when the source data is unavailable, it is challenging to just erase the wat…