# Safety Alignment for Vision Language Models

arXiv: https://arxiv.org/abs/2405.13581 · HTML: https://mlsanity.com/paper/2405.13581/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 22 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [On Evaluating Adversarial Robustness of Large Vision-Language Models](https://mlsanity.com/paper/2305.16934/) (2023)
- [MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2311.17600/) (2023)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [OneLLM: One Framework to Align All Modalities with Language](https://mlsanity.com/paper/2312.03700/) (2023)
- [Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models](https://mlsanity.com/paper/2402.02207/) (2024)
- [Meta-Transformer: A Unified Framework for Multimodal Learning](https://mlsanity.com/paper/2307.10802/) (2023)
- [How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs](https://mlsanity.com/paper/2311.16101/) (2023)
- [A Hierarchical Approach for Generating Descriptive Image Paragraphs](https://mlsanity.com/paper/1611.06607/) (2016)
- [SEED-Bench-2: Benchmarking Multimodal Large Language Models](https://mlsanity.com/paper/2311.17092/) (2023)
- [Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images](https://mlsanity.com/paper/2401.11170/) (2024)
- [AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors](https://mlsanity.com/paper/2310.17419/) (2023)

## Built on by (most cited first, 28 of 28)

- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning](https://mlsanity.com/paper/2505.11049/) (2025)
- [BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization](https://mlsanity.com/paper/2505.16640/) (2025)
- [AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving](https://mlsanity.com/paper/2412.15206/) (2024)
- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models](https://mlsanity.com/paper/2410.09047/) (2024)
- [JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models](https://mlsanity.com/paper/2505.19610/) (2025)
- [DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt](https://mlsanity.com/paper/2506.09353/) (2025)
- [Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions](https://mlsanity.com/paper/2507.22617/) (2025)
- [Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment](https://mlsanity.com/paper/2602.10161/) (2026)
- [Peering Behind the Shield: Guardrail Identification in Large Language Models](https://mlsanity.com/paper/2502.01241/) (2025)
- [Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models](https://mlsanity.com/paper/2411.04291/) (2024)
- [Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots](https://mlsanity.com/paper/2504.03735/) (2025)
- [Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities](https://mlsanity.com/paper/2507.11155/) (2025)
- [GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision](https://mlsanity.com/paper/2511.20994/) (2025)
- [WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections](https://mlsanity.com/paper/2605.15030/) (2026)
- [SafeCoT: Improving VLM Safety with Minimal Reasoning](https://mlsanity.com/paper/2506.08399/) (2025)
- [Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models](https://mlsanity.com/paper/2602.07013/) (2026)
- [From Evaluation to Defense: Advancing Safety in Video Large Language Models](https://mlsanity.com/paper/2505.16643/) (2025)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations](https://mlsanity.com/paper/2506.09067/) (2025)
- [LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models](https://mlsanity.com/paper/2509.25896/) (2025)
- [One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs](https://mlsanity.com/paper/2601.23041/) (2026)
- [Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models](https://mlsanity.com/paper/2509.25525/) (2025)
- [TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors](https://mlsanity.com/paper/2607.12571/) (2026)
- [SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models](https://mlsanity.com/paper/2609.03544/) (2026)
- [Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment](https://mlsanity.com/paper/2609.37837/) (2026)

## Abstract (arXiv)

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs is vulnerable, with attackers easily bypassing LLMs' safety alignment through visual modality features to launch attacks. To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images. For example, building upon the LLaVA-v1.5 model, we achieve a safety score of 8.26, surpassing the GPT-4V on the Red Teaming Visual Language Models (RTVLM) benchmark. Our method boasts ease of use, high flexibility, and strong controllability, and it enhances safety while having minimal impact on the model's general performance. Moreover, our alignment strategy also uncovers some possible risky content within commonly used open-source multimodal datasets. Our code will be open sourced after the anonymous review.