cs.CVNov 15, 2026

Fine-Grained RLAIF for Visual Safety: Learning to Zoom into Hazards for Multimodal Safety Alignment

Authors: Chunxue Xu, Yiwei Wang, Yujun Cai, Songze Li

Organizations: Southeast University, China

Abstract

Recent multimodal safety alignment heavily relies on a text-centric paradigm, assuming risks are explicit in language or globally prominent in images. However, real-world hazards are often visually subtle or peripheral, causing existing models to fail due to their reliance on coarse, global visual representations. In this work, we study fine-grained visual safety alignment and introduce a challenging 1,200-sample benchmark across four domains, where hazards necessitate localized inspection. To address this, we propose Fine-Grained RLAIF (FGR), a reinforcement learning framework that casts image zoom-in as a learnable perception policy. FGR employs a decomposed reward design to jointly align three core safety behaviors: (i) where to look via a visual evidence reward, (ii) when to act via a tool-formatting constraint, and (iii) how to reason via visually grounded safety explanations. FGR achieves accuracy ranging from 86.71% to 93.00%, consistently outperforming strong multimodal and agent-based baselines.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 15, 2025

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

Even modern AI models often remain vulnerable to multimodal queries in which harmful intent is embedded in images. A widely used approach for safety alignment is training with extensive multimodal safety datasets, but the costs of data curation and training are often prohibitive. To mitigate these costs, inference-time alignment has recently been explored, but they often lack generalizability across diverse multimodal jailbreaks and still incur notable overhead due to extra forward passes for response refinement or heavy pre-deployment calibration procedures. Here, we identify insufficient visual attention to safety-critical image regions as one of the key causes of multimodal safety failures. Building on this insight, we propose Multimodal Risk-Adaptive Steering (MoRAS), which enhances safety-critical visual attention via concise visual contexts for accurate multimodal risk assessment. This risk signal enables risk-adaptive steering for direct refusals, reducing inference overhead while remaining generalizable across diverse multimodal jailbreaks. Notably, MoRAS requires only a small calibration set to estimate multimodal risk, substantially reducing pre-deployment overhead. We conduct various empirical validations across multiple benchmarks and MLLM backbones, and observe that the proposed MoRAS consistently mitigates jailbreaks, preserves utility, and reduces computational overhead compared to state-of-the-art inference-time defenses.
Sep 2, 2026

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existing fine-tuning methods provide limited safety guarantees. Current approaches primarily rely on Lagrangian optimization that enforces safety through soft penalties on expected cumulative cost, often resulting in residual constraint violations or overly conservative behavior. Moreover, learning safety in visual domains is challenging due to the absence of dense per-step safety annotations. We propose ShieldVLA, a safety-aligned fine-tuning framework for VLA models based on Hamilton-Jacobi (HJ) reachability. ShieldVLA learns a model-free approximation of the HJ reachability value function directly from visual observations to estimate the safe operating region. The learned safety critic gates policy optimization by separating reward maximization within feasible regions from recovery near unsafe states, avoiding persistent reward-cost trade-offs. To enable scalable supervision in visual environments, we introduce rubric-based VLM safety scores that convert semantic safety feedback into structured critic targets without requiring manual cost labels. Across five navigation and manipulation benchmarks spanning multiple VLA backbones, ShieldVLA reduces cumulative safety cost by 57% on average and improves task success rate by +0.13 over SafeVLA.
Mar 9, 2026

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete and visually depictable, while safety concepts, like helpfulness, are abstract and lack visual referents. Inspired by the Self-Fulfilling mechanism underlying emergent misalignment, we propose Visual Self-Fulfilling Alignment (VSFA). VSFA fine-tunes vision-language models (VLMs) on neutral VQA tasks constructed around threat-related images, without any safety labels. Through repeated exposure to threat-related visual content, models internalize the implicit semantics of vigilance and caution, shaping safety-oriented personas. Experiments across multiple VLMs and safety benchmarks demonstrate that VSFA reduces the attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities. Our work extends the self-fulfilling mechanism from text to visual modalities, offering a label-free approach to VLMs alignment.