Understanding and Enhancing the Transferability of Jailbreaking Attacks
Paper
•
2502.03052
•
Published
Runqi Lin
RunqiLin
AI & ML interests
Adversarial Robustness, Jailbreaking
Organizations
None yet
authored
a
paper
7 months ago
authored
3
papers
over 1 year ago
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
Paper
•
2405.16262
•
Published
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
Paper
•
2404.08154
•
Published
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
Paper
•
2310.08847
•
Published