SALLIE: Safeguarding against Latent Language and Image Exploits

Large Language Models LLMs and Vision-Language Models VLMs remain highly vulnerable to textual and visual jailbreaks, as well as prompt injections arXiv:2307.15043, Greshake et al., 2023, arXiv:2306.13213. Existing defenses often degrade performance through complex input transformations or treat...