4 papers
FLARE: Toward Universal Dataset Purification against Backdoor Attacks
Linshan Hou, Wei Luo, Zhongyun Hua +3
Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries poison datasets with adversary-specified triggers to implant hidden backdoors, enabling malicious…
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…
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning
Ruining Sun, Hongsheng Hu, Wei Luo +4
With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the rese…
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
Yechao Zhang, Yuxuan Zhou, Tianyu Li +4
Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of…