📚 Papers & Code

Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack

Patch-wise Attack for Fooling Deep Neural Network

Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks

Frequency Domain Model Augmentation for Adversarial Attack

Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization

Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation

FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism

Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs