通过动态调整视觉令牌权重，提升多模态模型对抗攻击的鲁棒性。
Dynamic Token Reweighting for Robust Vision-Language Models
- 基于键值缓存优化，动态重加权视觉令牌。
- 在多个攻击基准上显著提升防御效果，且不影响正常任务表现。
- 无需额外训练数据或图像转文本，适合部署于实际系统。
大型视觉语言模型（VLMs）极易受到多模态越狱攻击，此类攻击利用视觉与文本的交互绕过安全防护机制。本文提出DTR，一种新型推理时防御方法，通过优化模型的键值（KV）缓存来缓解多模态越狱攻击。我们提出一种新的视觉模态引发的安全相关分布偏移形式化表达，使DTR能够动态调整视觉令牌权重，在抑制对抗性视觉输入影响的同时，保持模型通用能力与推理效率。在多种VLM和攻击基准上的广泛评估表明，DTR在攻击鲁棒性与良性任务性能方面均优于现有防御方法，首次成功将键值缓存优化应用于多模态基础模型的安全增强。代码已开源：https://github.com/TanqiuJiang/DTR。
原文摘要 · Abstract (English)
Large vision-language models (VLMs) are highly vulnerable to multimodal 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 DTR 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 at: https://github.com/TanqiuJiang/DTR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。