Lihe Zhang
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper reinterprets catastrophic overfitting (CO) in Fast Adversarial Training (FAT) as a weak backdoor mechanism, proposing backdoor-inspired strategies to mitigate this generalization failure.
The paper proposes a Distribution-aware Dynamic Guidance (DDG) strategy to mitigate catastrophic overfitting and the robustness-accuracy trade-off inherent in Fast Adversarial Training (FAT) by dynamically adjusting perturbation budgets and supervision signals based on sample confidence.
CoreUnlearn introduces a novel framework that disentangles and removes undesirable concepts from text-guided diffusion models by targeting specific, erasure-critical components of the concept embedding, thereby achieving effective unlearning with minimal performance degradation.
Papers
CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
CoreUnlearn introduces a novel framework that disentangles and removes undesirable concepts from text-guided diffusion models by targeting specific, erasure-critical components of the concept embeddin…