Robustifying Vision-Language Models via Dynamic Token Reweighting
Journal:
arXiv
Published Date:
May 22, 2025
Abstract
Large vision-language models (VLMs) are highly vulnerable to jailbreak
attacks that exploit visual-textual interactions to bypass safety guardrails.
In this paper, we present DTR, a novel inference-time defense that mitigates
multimodal jailbreak attacks through optimizing the model's key-value (KV)
caches. Rather than relying on curated safety-specific data or costly
image-to-text conversion, we introduce a new formulation of the safety-relevant
distributional shift induced by the visual modality. This formulation enables
DTR to dynamically adjust visual token weights, minimizing the impact of
adversarial visual inputs while preserving the model's general capabilities and
inference efficiency. Extensive evaluation across diverse VLMs and attack
benchmarks demonstrates that \sys outperforms existing defenses in both attack
robustness and benign task performance, marking the first successful
application of KV cache optimization for safety enhancement in multimodal
foundation models. The code for replicating DTR is available:
https://anonymous.4open.science/r/DTR-2755 (warning: this paper contains
potentially harmful content generated by VLMs.)
