SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability

• URL: http://arxiv.org/abs/2510.23960v1
• Date: Tue, 28 Oct 2025 00:35:59 GMT
• Title: SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability
• Authors: Peiyang Xu, Minzhou Pan, Zhaorun Chen, Shuang Yang, Chaowei Xiao, Bo Li,
• Abstract summary: We introduce SafeVision, a novel image guardrail that integrates human-like reasoning to enhance adaptability and transparency.<n>Our approach incorporates an effective data collection and generation framework, a policy-following training pipeline, and a customized loss function.<n>We show that SafeVision achieves state-of-the-art performance on different benchmarks.
• Score: 49.074914896839466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ReVision : A Post-Hoc, Vision-Based Technique for Replacing Unacceptable Concepts in Image Generation Pipeline [0.695942427153803]
  ReVision is a training-free, prompt-based, post-hoc safety framework for image-generation pipeline.<n>It selectively edits unsafe concepts without altering the underlying generator.<n>It uses the Gemini-2.5-Flash model as a generic policy-violating concept detector.
  arXiv  Detail & Related papers  (2026-02-22T12:30:01Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models [74.11062256255387]
  Text-to-image models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce harmful content.<n>We introduce SafeGuider, a two-step framework designed for robust safety control without compromising generation quality.<n>SafeGuider demonstrates exceptional effectiveness in minimizing attack success rates, achieving a maximum rate of only 5.48% across various attack scenarios.
  arXiv  Detail & Related papers  (2025-10-05T10:24:48Z)
• PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation [30.2092299298228]
  Text-to-image (T2I) models are vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery.<n>We propose PromptSafe, a gated prompt tuning framework that combines a lightweight, text-only supervised soft embedding with an inference-time gated control network.<n>We show that PromptSafe achieves a SOTA unsafe generation rate (2.36%) while preserving high benign fidelity.
  arXiv  Detail & Related papers  (2025-08-02T09:09:40Z)
• HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model [58.12612140992874]
  We introduce a holistic safety dataset and benchmark, textbfHoliSafe, that spans all five safe/unsafe image-text combinations.<n>We also propose a novel modular framework for enhancing VLM safety with a visual guard module (VGM) designed to assess the harmfulness of input images.<n> Experiments show that Safe-VLM with VGM, trained on our HoliSafe, achieves state-of-the-art safety performance across multiple VLM benchmarks.
  arXiv  Detail & Related papers  (2025-06-05T07:26:34Z)
• Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense [90.71884758066042]
  Large vision-language models (LVLMs) introduce a unique vulnerability: susceptibility to malicious attacks via visual inputs.<n>We propose ESIII (Embedding Security Instructions Into Images), a novel methodology for transforming the visual space from a source of vulnerability into an active defense mechanism.
  arXiv  Detail & Related papers  (2025-03-14T17:39:45Z)
• Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models [25.606641582511106]
  We propose a novel dataset that integrates multi-image inputs with safety Chain-of-Thought (CoT) labels as fine-grained reasoning logic to improve model performance.<n>Our experiments demonstrate that fine-tuning InternVL2.5-8B with MIS significantly outperforms both powerful open-source models and API-based models in challenging multi-image tasks.
  arXiv  Detail & Related papers  (2025-01-30T17:59:45Z)
• Adversarial Prompt Tuning for Vision-Language Models [86.5543597406173]
  Adversarial Prompt Tuning (AdvPT) is a technique to enhance the adversarial robustness of image encoders in Vision-Language Models (VLMs) We demonstrate that AdvPT improves resistance against white-box and black-box adversarial attacks and exhibits a synergistic effect when combined with existing image-processing-based defense techniques.
  arXiv  Detail & Related papers  (2023-11-19T07:47:43Z)

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.