Ranjie Duan

7

Papers

49

Total Citations

Papers (7)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models

Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles

Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink

Towards Robust Vision Transformer

AdvDrop: Adversarial Attack to DNNs by Dropping Information

Enhance the Visual Representation via Discrete Adversarial Training

NeurIPS 2022arXiv