Can I read Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy on EtoBox?

Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy by Jeong, Joonhyun; Bae, Seyun; Jung, Yeonsung; Hwang, Jaeryong; Yang, Eunho is a scholarly article available to read on EtoBox.

What is Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy about?

Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize across both language and vision tasks, LLMs and MLLMs have shown vulnerability to jailbreaking, generating textual outputs that undermine safety, ethical, and bias standards when exposed to harmful or sensitive inputs. With the recent advancement of safety alignment via preference-tuning from human feedback, LLMs and MLLMs have been equipped with safety guardrails to yield safe, ethical, and fair responses with regard to harmful inputs. However, despite the significance of safety alignment, research on the vulnerabilities remains largely underexplored. In this paper, we investigate the unexplored vulnerability of the safety alignment, examining its ability to consistently provide safety guarantees for out-of-distribution(OOD)-ifying harmful inputs that may fall outside the aligned data distribution. Our key observation is that OOD-ifying the vanilla harmful inputs highly increases the uncertainty of the model to discern the malicious intent within the input, leading to a higher chance of being jailbroken. Exploiting this vulnerability, we propose JOOD, a new Jailbreak framew

Author

Jeong, Joonhyun; Bae, Seyun; Jung, Yeonsung; Hwang, Jaeryong; Yang, Eunho

Published

2025

Language

EN