# SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability

arXiv: https://arxiv.org/abs/2510.23960 · HTML: https://mlsanity.com/paper/2510.23960/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 34 of its 67 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 34)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?](https://mlsanity.com/paper/2202.06675/) (2022)
- [ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning](https://mlsanity.com/paper/2503.22738/) (2025)
- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models](https://mlsanity.com/paper/2402.05935/) (2024)
- [SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models](https://mlsanity.com/paper/2404.06666/) (2024)
- [UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images](https://mlsanity.com/paper/2405.03486/) (2024)

## Built on by (most cited first, 4 of 4)

- [Towards Policy-Adaptive Image Guardrail: Benchmark and Method](https://mlsanity.com/paper/2603.01228/) (2026)
- [SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning](https://mlsanity.com/paper/2606.22873/) (2026)
- [CompAgent: An Agentic Framework for Visual Compliance Verification](https://mlsanity.com/paper/2511.00171/) (2025)
- [PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails](https://mlsanity.com/paper/2607.05910/) (2026)

## Abstract (arXiv)

With the rapid proliferation of digital media, the need for efficient and transparent safeguards against unsafe content is more critical than ever. Traditional image guardrail models, constrained by predefined categories, often misclassify content due to their pure feature-based learning without semantic reasoning. Moreover, these models struggle to adapt to emerging threats, requiring costly retraining for new threats. To address these limitations, we introduce SafeVision, a novel image guardrail that integrates human-like reasoning to enhance adaptability and transparency. Our approach incorporates an effective data collection and generation framework, a policy-following training pipeline, and a customized loss function. We also propose a diverse QA generation and training strategy to enhance learning effectiveness. SafeVision dynamically aligns with evolving safety policies at inference time, eliminating the need for retraining while ensuring precise risk assessments and explanations. Recognizing the limitations of existing unsafe image benchmarks, which either lack granularity or cover limited risks, we introduce VisionHarm, a high-quality dataset comprising two subsets: VisionHarm Third-party (VisionHarm-T) and VisionHarm Comprehensive(VisionHarm-C), spanning diverse harmful categories. Through extensive experiments, we show that SafeVision achieves state-of-the-art performance on different benchmarks. SafeVision outperforms GPT-4o by 8.6% on VisionHarm-T and by 15.5% on VisionHarm-C, while being over 16x faster. SafeVision sets a comprehensive, policy-following, and explainable image guardrail with dynamic adaptation to emerging threats.