Robustifying Vision-Language Models via Dynamic Token Reweighting

• URL: http://arxiv.org/abs/2505.17132v2
• Date: Sat, 07 Jun 2025 19:22:05 GMT
• Title: Robustifying Vision-Language Models via Dynamic Token Reweighting
• Authors: Tanqiu Jiang, Jiacheng Liang, Rongyi Zhu, Jiawei Zhou, Fenglong Ma, Ting Wang,
• Abstract summary: Large vision-language models (VLMs) are highly vulnerable to jailbreak attacks.<n>We present a novel inference-time defense that mitigates multimodal jailbreak attacks.<n>We introduce a new formulation of the safety-relevant distributional shift induced by the visual modality.
• Score: 28.675118345987887
• License: http://creativecommons.org/licenses/by/4.0/
• 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. (warning: this paper contains potentially harmful content generated by VLMs.)

Related papers

• Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense [90.71884758066042]
  Large vision-language models (LVLMs) introduce a unique vulnerability: susceptibility to malicious attacks via visual inputs.<n>We propose ESIII (Embedding Security Instructions Into Images), a novel methodology for transforming the visual space from a source of vulnerability into an active defense mechanism.
  arXiv  Detail & Related papers  (2025-03-14T17:39:45Z)
• CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models [16.5022773312661]
  We propose a universal certified defence framework to safeguard large vision-language models against jailbreak attacks.<n>First, we proposed a novel distance metric to quantify semantic discrepancies between malicious and intended responses.<n>Then, we devise a regressed certification approach that employs randomized smoothing to provide formal robustness guarantees.
  arXiv  Detail & Related papers  (2025-03-08T17:33:55Z)
• Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models [26.656858396343726]
  Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations.<n>Existing methods seek to mitigate these risks by applying constrained adversarial fine-tuning to CLIP vision encoders on ImageNet-scale data.<n>We explore an alternative approach of leveraging existing vision classification models that have been adversarially pre-trained on large-scale data.
  arXiv  Detail & Related papers  (2025-02-03T17:59:45Z)
• Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update [8.739132798784777]
  Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content.<n>We propose an textbfinternal activation revision approach that efficiently revises activations during generation.<n>Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity.
  arXiv  Detail & Related papers  (2025-01-24T06:17:22Z)
• Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning [19.638259197558625]
  Multimodal contrastive learning models (e.g., CLIP) can learn high-quality representations from large-scale image-text datasets.<n>They exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns.<n>We propose Repulsive Visual Prompt Tuning (RVPT), a novel defense approach that employs deep visual prompt tuning with a specially designed feature-repelling loss.
  arXiv  Detail & Related papers  (2024-12-29T08:09:20Z)
• Retention Score: Quantifying Jailbreak Risks for Vision Language Models [60.48306899271866]
  Vision-Language Models (VLMs) are integrated with Large Language Models (LLMs) to enhance multi-modal machine learning capabilities.<n>This paper aims to assess the resilience of VLMs against jailbreak attacks that can compromise model safety compliance and result in harmful outputs.<n>To evaluate a VLM's ability to maintain its robustness against adversarial input perturbations, we propose a novel metric called the textbfRetention Score.
  arXiv  Detail & Related papers  (2024-12-23T13:05:51Z)
• Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks [34.40254709148148]
  Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding. Their potential safety and robustness issues raise concerns that adversaries may evade the system and cause these models to generate toxic content through malicious attacks. We present Chain of Attack (CoA), which iteratively enhances the generation of adversarial examples based on the multi-modal semantic update.
  arXiv  Detail & Related papers  (2024-11-24T05:28:07Z)
• Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models [17.663550432103534]
  Multimodal Large Language Models (MLLMs) extend the capacity of LLMs to understand multimodal information comprehensively. These models are susceptible to jailbreak attacks, where malicious users can break the safety alignment of the target model and generate misleading and harmful answers. We propose Cross-modality Information DEtectoR (CIDER), a plug-and-play jailbreaking detector designed to identify maliciously perturbed image inputs.
  arXiv  Detail & Related papers  (2024-07-31T15:02:46Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models [65.23688155159398]
  Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images. We propose a multimodal instruction backdoor attack, namely VL-Trojan.
  arXiv  Detail & Related papers  (2024-02-21T14:54:30Z)
• Adversarial Prompt Tuning for Vision-Language Models [86.5543597406173]
  Adversarial Prompt Tuning (AdvPT) is a technique to enhance the adversarial robustness of image encoders in Vision-Language Models (VLMs) We demonstrate that AdvPT improves resistance against white-box and black-box adversarial attacks and exhibits a synergistic effect when combined with existing image-processing-based defense techniques.
  arXiv  Detail & Related papers  (2023-11-19T07:47:43Z)
• Defending Variational Autoencoders from Adversarial Attacks with MCMC [74.36233246536459]
  Variational autoencoders (VAEs) are deep generative models used in various domains. As previous work has shown, one can easily fool VAEs to produce unexpected latent representations and reconstructions for a visually slightly modified input. Here, we examine several objective functions for adversarial attacks construction, suggest metrics assess the model robustness, and propose a solution.
  arXiv  Detail & Related papers  (2022-03-18T13:25:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.