5 papers
Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
Jun Liu, Leo Yu Zhang, Fengpeng Li +2
Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite recent progress, existing approaches…
FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection
Zhilin Tu, Kemou Li, Fengpeng Li +3
The rapid iteration and widespread dissemination of deepfake technology have posed severe challenges to information security, making robust and generalizable detection of AI-genera…
LLM Unlearning with LLM Beliefs
Kemou Li, Qizhou Wang, Yue Wang +4
Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods gen…
AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
Fengpeng Li, Kemou Li, Qizhou Wang +2
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by…
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
Fengpeng Li, Kemou Li, Haiwei Wu +2
To protect deep neural networks (DNNs) from adversarial attacks, adversarial training (AT) is developed by incorporating adversarial examples (AEs) into model training. Recent stud…