VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards. Inspired by the insight that reasoning across modalities is key to preempting intricate vulnerabilities, we propose a novel direction for VLM safety: multimodal reasoning-driven prompt rewriting. To this end, we introduce VLMGuard-R1, a proactive framework that refines user inputs through a reasoning-guided rewriter, dynamically interpreting text-image interactions to deliver refined prompts that bolster safety across diverse VLM architectures without altering their core parameters. To achieve this, we devise a three-stage reasoning pipeline to synthesize a dataset that trains the rewriter to infer subtle threats, enabling tailored, actionable responses over generic refusals. Extensive experiments across three benchmarks with five VLMs reveal that VLMGuard-R1 outperforms four baselines. In particular, VLMGuard-R1 achieves a remarkable 43.59\% increase in average safety across five models on the SIUO benchmark.
Code (0)
등록된 구현이 없습니다.
Tasks
Multimodal ReasoningSafety AlignmentSimilar Papers 제목 키워드 기반
VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal perception and generation, yet their safety alignment remains a critical challenge.Existing defenses and vulnerable to multimodal jailb…
VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to com…
AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradati…
Reinforcement LearningRoad Rage Reasoning with Vision-language Models (VLMs): Task Definition and Evaluation Dataset
Road rage, triggered by driving-related stimuli such as traffic congestion and aggressive driving, poses a significant threat to road safety. Previous research on road rage regulation has primarily focused on response su…
Scene UnderstandingStealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT
Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safet…