CRAICLLGDec 12, 2025

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring

arXiv:2512.12069v27 citationsh-index: 13Has Code
Originality Highly original
AI Analysis

This addresses the need for generalizable and efficient jailbreak detection in LVLMs, offering a practical solution for safer deployment.

The paper tackles the problem of multimodal jailbreak attacks on Large Vision-Language Models (LVLMs) by proposing Representational Contrastive Scoring (RCS), which uses internal model representations to separate benign and malicious inputs, achieving state-of-the-art performance on a challenging evaluation protocol.

Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and efficient for practical deployment. Many current strategies fall short, either targeting specific attack patterns, which limits generalization, or imposing high computational overhead. While lightweight anomaly-detection methods offer a promising direction, we find that their common one-class design tends to confuse novel benign inputs with malicious ones, leading to unreliable over-rejection. To address this, we propose Representational Contrastive Scoring (RCS), a framework built on a key insight: the most potent safety signals reside within the LVLM's own internal representations. Our approach inspects the internal geometry of these representations, learning a lightweight projection to maximally separate benign and malicious inputs in safety-critical layers. This enables a simple yet powerful contrastive score that differentiates true malicious intent from mere novelty. Our instantiations, MCD (Mahalanobis Contrastive Detection) and KCD (K-nearest Contrastive Detection), achieve state-of-the-art performance on a challenging evaluation protocol designed to test generalization to unseen attack types. This work demonstrates that effective jailbreak detection can be achieved by applying simple, interpretable statistical methods to the appropriate internal representations, offering a practical path towards safer LVLM deployment. Our code is available on Github https://github.com/sarendis56/Jailbreak_Detection_RCS.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes