When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2509.12060v2
• Date: Tue, 16 Sep 2025 06:19:02 GMT
• Title: When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models
• Authors: Wei Cai, Shujuan Liu, Jian Zhao, Ziyan Shi, Yusheng Zhao, Yuchen Yuan, Tianle Zhang, Chi Zhang, Xuelong Li,
• Abstract summary: We introduce Safe-Semantics-but-Unsafe-Interpretation (SSUI), the first dataset featuring interpretable reasoning paths tailored for a cross-modal challenge.<n>A novel training framework, Safety-aware Reasoning Path Optimization (SRPO), is also designed based on the SSUI dataset.<n> Experimental results show that our SRPO-trained models achieve state-of-the-art results on key safety benchmarks.
• Score: 50.66979825532277
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to the difficulty of MLLMs maintaining safety alignment through long-chain reasoning. To address this issue, we introduce Safe-Semantics-but-Unsafe-Interpretation (SSUI), the first dataset featuring interpretable reasoning paths tailored for such a cross-modal challenge. A novel training framework, Safety-aware Reasoning Path Optimization (SRPO), is also designed based on the SSUI dataset to align the MLLM's internal reasoning process with human safety values. Experimental results show that our SRPO-trained models achieve state-of-the-art results on key safety benchmarks, including the proposed Reasoning Path Benchmark (RSBench), significantly outperforming both open-source and top-tier commercial MLLMs.

Related papers

• Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models [46.51961683413124]
  This paper introduces the concept of Implicit Reasoning Safety, a vulnerability in LVLMs.<n>Our demonstrations show that even simple In-Context Learning with SSUI significantly mitigates these implicit multimodal threats.
  arXiv  Detail & Related papers  (2025-08-12T13:26:06Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models [17.824240702928133]
  Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities.<n>Existing safety alignment approaches fall short in addressing the complex and nuanced threats posed by multimodal inputs.<n>MSR-Align supports fine-grained, deliberative reasoning over standardized safety policies across both vision and text modalities.
  arXiv  Detail & Related papers  (2025-06-24T02:37:59Z)
• USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models [31.412080488801507]
  Unified Safety Benchmarks (USB) is one of the most comprehensive evaluation benchmarks in MLLM safety.<n>Our benchmark features high-quality queries, extensive risk categories, comprehensive modal combinations, and encompasses both vulnerability and oversensitivity evaluations.
  arXiv  Detail & Related papers  (2025-05-26T08:39:14Z)
• DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models [37.104276926258095]
  Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.<n>We introduce textbfDREAM (textittextbfDisentangling textbfRisks to textbfEnhance Safety textbfAlignment in textbfMLLMs), a novel approach that enhances safety alignment in MLLMs through supervised fine-tuning and iterative Reinforcement Learning from AI Feedback.
  arXiv  Detail & Related papers  (2025-04-25T03:54:24Z)
• SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models [50.34706204154244]
  Acquiring reasoning capabilities catastrophically degrades inherited safety alignment.<n>Certain scenarios suffer 25 times higher attack rates.<n>Despite tight reasoning-answer safety coupling, MLRMs demonstrate nascent self-correction.
  arXiv  Detail & Related papers  (2025-04-09T06:53:23Z)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model [73.8765529028288]
  We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment.<n>To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations.<n>Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-21T16:14:15Z)
• 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)

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.