 SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image GenerationIEEE Transactions on Information Forensics and Security (TIFS), 2025 |
 Robust and Transferable Backdoor Attacks Against Deep Image Compression
With Selective Frequency PriorIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 |
 Uncovering, Explaining, and Mitigating the Superficial Safety of
Backdoor DefenseNeural Information Processing Systems (NeurIPS), 2024 |
 Mitigating Memorization In Language Models Mansi Sakarvadia Aswathy Ajith Arham Khan Nathaniel Hudson Caleb Geniesse Kyle Chard Yaoqing Yang Ian Foster Michael W. Mahoney |
 Purify Unlearnable Examples via Rate-Constrained Variational
AutoencodersInternational Conference on Machine Learning (ICML), 2024 |
