[Submitted on 24 Sep 2025 (v1), last revised 22 Oct 2025 (this version, v2)]

JaiLIP: A new image-based jailbreak attack method for Vision-Language Models

This paper introduces JaiLIP (Jailbreaking with Loss-guided Image Perturbation), a novel attack method targeting Vision-Language Models (VLMs). The technique generates adversarial images by minimizing a joint objective that combines mean squared error loss between clean and adversarial images with the model's harmful-output loss. The method produces highly e