# SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2410.18927 · HTML: https://mlsanity.com/paper/2410.18927/

## Key facts

- Cited by 69 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 69 of its 113 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## 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 69)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)

## Built on by (most cited first, 30 of 69)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety](https://mlsanity.com/paper/2507.06134/) (2025)
- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models](https://mlsanity.com/paper/2502.11054/) (2025)
- [Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning](https://mlsanity.com/paper/2508.16949/) (2025)
- [A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges](https://mlsanity.com/paper/2501.02189/) (2025)
- [Manipulating Multimodal Agents via Cross-Modal Prompt Injection](https://mlsanity.com/paper/2504.14348/) (2025)
- [AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions](https://mlsanity.com/paper/2506.14697/) (2025)
- [IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves](https://mlsanity.com/paper/2411.00827/) (2024)
- [Visual Adversarial Attack on Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2411.18275/) (2024)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains](https://mlsanity.com/paper/2507.23486/) (2025)
- [Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings](https://mlsanity.com/paper/2503.15092/) (2025)
- [o3-mini vs DeepSeek-R1: Which One is Safer?](https://mlsanity.com/paper/2501.18438/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models](https://mlsanity.com/paper/2504.15512/) (2025)
- [RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic](https://mlsanity.com/paper/2512.21220/) (2025)
- [Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation](https://mlsanity.com/paper/2501.17749/) (2025)
- [When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models](https://mlsanity.com/paper/2602.18739/) (2026)
- [Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025](https://mlsanity.com/paper/2506.12430/) (2025)
- [MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models](https://mlsanity.com/paper/2505.14728/) (2025)
- [USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2505.23793/) (2025)
- [Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing](https://mlsanity.com/paper/2510.01243/) (2025)
- [Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies](https://mlsanity.com/paper/2505.14972/) (2025)
- [Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers](https://mlsanity.com/paper/2505.16241/) (2025)
- [ASTRAL: Automated Safety Testing of Large Language Models](https://mlsanity.com/paper/2501.17132/) (2025)
- [Universal Adversarial Attack on Aligned Multimodal LLMs](https://mlsanity.com/paper/2502.07987/) (2025)
- [POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models](https://mlsanity.com/paper/2505.06579/) (2025)
- [Quantifying CBRN Risk in Frontier Models](https://mlsanity.com/paper/2510.21133/) (2025)
- [Failures to Surface Harmful Contents in Video Large Language Models](https://mlsanity.com/paper/2508.10974/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks for MLLMs show limitations in query quality and evaluation reliability limiting the detection of model safety implications as MLLMs continue to evolve. In this paper, 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 that aims to address the above limitations, respectively. We first design an automatic safety dataset generation pipeline, where we employ a set of LLM judges to recognize and categorize the risk scenarios that are most harmful and diverse for MLLMs; based on the taxonomy, we further ask these judges to generate high-quality harmful queries accordingly resulting in 23 risk scenarios with 2,300 multi-modal harmful query pairs. During safety evaluation, we draw inspiration from the jury system in judicial proceedings and pioneer the jury deliberation evaluation protocol that adopts collaborative LLMs to evaluate whether target models exhibit specific harmful behaviors, providing a reliable and unbiased assessment of content security risks. In addition, our benchmark can also be extended to the audio modality showing high scalability and potential. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs (e.g., GPT-4o, Gemini), where we revealed widespread safety issues in existing MLLMs and instantiated several insights on MLLM safety performance such as image quality and parameter size.