2 papers
cs.CV2026
REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
Yong Zou, Haoran Li, Fanxiao Li +5
Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generat…
cs.CV2024
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
Linyu Tang, Lei Zhang
Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to subtle adversarial perturbations, prompting the development of many advanced adversarial def…