PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality

• URL: http://arxiv.org/abs/2508.18649v1
• Date: Tue, 26 Aug 2025 03:45:19 GMT
• Title: PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
• Authors: Nanxi Li, Zhengyue Zhao, Chaowei Xiao,
• Abstract summary: PRISM (Principled Reasoning for Integrated Safety in Multimodality) is a system2-like framework that aligns vision-language models (VLMs)<n>Our framework consists of two key components: PRISM-CoT, a dataset that teaches safety-aware chain-of-thought reasoning, and PRISM-DPO, generated via Monte Carlo Tree Search (MCTS)<n> Comprehensive evaluations demonstrate PRISM's effectiveness, achieving remarkably low attack success rates including 0.15% on JailbreakV-28K for Qwen2-VL and 90% improvement over the previous best method on VLBreak for LLaVA-1.5.
• Score: 41.04710068888387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To this end, we introduce PRISM (Principled Reasoning for Integrated Safety in Multimodality), a system2-like framework that aligns VLMs by embedding a structured, safety-aware reasoning process. Our framework consists of two key components: PRISM-CoT, a dataset that teaches safety-aware chain-of-thought reasoning, and PRISM-DPO, generated via Monte Carlo Tree Search (MCTS) to further refine this reasoning through Direct Preference Optimization to help obtain a delicate safety boundary. Comprehensive evaluations demonstrate PRISM's effectiveness, achieving remarkably low attack success rates including 0.15% on JailbreakV-28K for Qwen2-VL and 90% improvement over the previous best method on VLBreak for LLaVA-1.5. PRISM also exhibits strong robustness against adaptive attacks, significantly increasing computational costs for adversaries, and generalizes effectively to out-of-distribution challenges, reducing attack success rates to just 8.70% on the challenging multi-image MIS benchmark. Remarkably, this robust defense is achieved while preserving, and in some cases enhancing, model utility. To promote reproducibility, we have made our code, data, and model weights available at https://github.com/SaFoLab-WISC/PRISM.

Related papers

• Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization [51.12422886183246]
  Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks.<n>Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the dynamic interplay between evolving threats and safeguards in real-world web contexts.<n>We propose ACE-Safety, a novel framework that jointly optimize attack and defense models by seamlessly integrating two key innovative procedures.
  arXiv  Detail & Related papers  (2025-11-24T15:23:41Z)
• Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models [54.61181161508336]
  We introduce Multi-Faceted Attack (MFA), a framework that exposes general safety vulnerabilities in leading defense-equipped Vision-Language Models (VLMs)<n>The core component of MFA is the Attention-Transfer Attack (ATA), which hides harmful instructions inside a meta task with competing objectives.<n>MFA achieves a 58.5% success rate and consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-20T07:12:54Z)
• SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models [66.71948519280669]
  Multimodal Large Reasoning Models (MLRMs) demonstrate impressive crossmodal reasoning but often amplify safety risks under adversarial prompts.<n> Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving models to implicit risks.<n>We propose SaFeR-VLM, which integrates four components and supports dynamic and interpretable safety decisions beyond surface-level filtering.
  arXiv  Detail & Related papers  (2025-10-08T10:39:12Z)
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking [3.718606661938873]
  We propose a novel and effective jailbreak framework inspired by Return-Oriented Programming (ROP) techniques from software security.<n>Our approach decomposes a harmful instruction into a sequence of individually benign visual gadgets.<n>Our findings reveal a critical and underexplored vulnerability that exploits the compositional reasoning abilities of LVLMs.
  arXiv  Detail & Related papers  (2025-07-29T07:13:56Z)
• T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks [67.91652526657599]
  We formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called T2V-OptJail.<n>We conduct large-scale experiments on several T2V models, covering both open-source models and real commercial closed-source models.<n>The proposed method improves 11.4% and 10.0% over the existing state-of-the-art method in terms of attack success rate.
  arXiv  Detail & Related papers  (2025-05-10T16:04:52Z)
• Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback [34.01716144973483]
  Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants.<n>How can we ensure safety alignment of MLLMs to prevent undesired behaviors?<n>In this work, we present the first exploration of the Safe RLHF-V -- the first multimodal safety alignment framework.
  arXiv  Detail & Related papers  (2025-03-22T07:40:20Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [65.41451412400609]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks [17.75247947379804]
  We present the first adversarial training paradigm tailored to defend against jailbreak attacks during the MLLM training phase.<n>We introduce Projection Layer Against Adversarial Training (ProEAT), an end-to-end AT framework.<n>ProEAT achieves state-of-the-art defense performance, outperforming existing baselines by an average margin of +34% across text and image modalities.
  arXiv  Detail & Related papers  (2025-03-05T14:13:35Z)
• Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees [6.792743621449621]
  Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts.<n>Existing L2D frameworks assume clean inputs and are vulnerable to adversarial perturbations that can manipulate query allocation.<n>We present the first comprehensive study of adversarial robustness in two-stage L2D systems.
  arXiv  Detail & Related papers  (2025-02-03T03:44:35Z)
• 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)

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.