Scaling Compute Is Not All You Need for Adversarial Robustness

On the Adversarial Robustness of Multi-Modal Foundation Models ICCV’23

On the Robustness of Large Multimodal Models Against Image Adversarial Attacks ArXiv Dec’23 

On Evaluating Adversarial Robustness of Large Vision-Language Models NeurIPS’23

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models ICLR’24 submission

Non-targeted Adversarial Attacks on Vision-Language Models via Maximizing Information Entropy ICLR’24 submission

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models NeurIPS’23 

Visual Adversarial Examples Jailbreak Aligned Large Language Models ArXiv July’23

How Robust is Google's Bard to Adversarial Image Attacks? ArXiv Sept’23

Baseline Defenses for Adversarial Attacks Against Aligned Language Models ICLR’24 submission