# Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

arXiv: https://arxiv.org/abs/2411.10414 · HTML: https://mlsanity.com/paper/2411.10414/

## Key facts

- Cited by 129 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 29 of its 33 references that are in the map.
- First posted on arXiv 15 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Safety Alignment Should Be Made More Than Just a Few Tokens Deep](https://mlsanity.com/paper/2406.05946/) (2024)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content](https://mlsanity.com/paper/2403.13031/) (2024)
- [Introducing v0.5 of the AI Safety Benchmark from MLCommons](https://mlsanity.com/paper/2404.12241/) (2024)
- [Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them](https://mlsanity.com/paper/2107.11630/) (2021)
- [Backtracking Improves Generation Safety](https://mlsanity.com/paper/2409.14586/) (2024)
- [Gradient-based Jailbreak Images for Multimodal Fusion Models](https://mlsanity.com/paper/2410.03489/) (2024)

## Built on by (most cited first, 30 of 129)

- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)
- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [Agentic Web: Weaving the Next Web with AI Agents](https://mlsanity.com/paper/2507.21206/) (2025)
- [GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning](https://mlsanity.com/paper/2505.11049/) (2025)
- [ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails](https://mlsanity.com/paper/2502.13458/) (2025)
- [Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback](https://mlsanity.com/paper/2503.17682/) (2025)
- [Security Concerns for Large Language Models: A Survey](https://mlsanity.com/paper/2505.18889/) (2025)
- [Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs](https://mlsanity.com/paper/2505.11842/) (2025)
- [CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications](https://mlsanity.com/paper/2508.01710/) (2025)
- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [WebGuard: Building a Generalizable Guardrail for Web Agents](https://mlsanity.com/paper/2507.14293/) (2025)
- [Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model](https://mlsanity.com/paper/2505.06538/) (2025)
- [DynaGuard: A Dynamic Guardian Model With User-Defined Policies](https://mlsanity.com/paper/2509.02563/) (2025)
- [ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving](https://mlsanity.com/paper/2502.00937/) (2025)
- [T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model](https://mlsanity.com/paper/2510.22300/) (2025)
- [Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning](https://mlsanity.com/paper/2503.11832/) (2025)
- [Position: Adversarial ML for LLMs Is Not Making Any Progress](https://mlsanity.com/paper/2502.02260/) (2025)
- [Learning to Steer: Input-dependent Steering for Multimodal LLMs](https://mlsanity.com/paper/2508.12815/) (2025)
- [MSTS: A Multimodal Safety Test Suite for Vision-Language Models](https://mlsanity.com/paper/2501.10057/) (2025)
- [Shape it Up! Restoring LLM Safety during Finetuning](https://mlsanity.com/paper/2505.17196/) (2025)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2505.23793/) (2025)
- [BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation](https://mlsanity.com/paper/2504.16907/) (2025)
- [HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model](https://mlsanity.com/paper/2506.04704/) (2025)
- [LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops](https://mlsanity.com/paper/2506.14493/) (2025)
- [Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection](https://mlsanity.com/paper/2510.09694/) (2025)
- [HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark](https://mlsanity.com/paper/2604.13954/) (2026)
- [VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety](https://mlsanity.com/paper/2510.18214/) (2025)
- [ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs](https://mlsanity.com/paper/2505.14035/) (2025)

## Abstract (arXiv)

We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification) and outputs (response classification). Unlike the previous text-only Llama Guard versions (Inan et al., 2023; Llama Team, 2024b,a), it is specifically designed to support image reasoning use cases and is optimized to detect harmful multimodal (text and image) prompts and text responses to these prompts. Llama Guard 3 Vision is fine-tuned on Llama 3.2-Vision and demonstrates strong performance on the internal benchmarks using the MLCommons taxonomy. We also test its robustness against adversarial attacks. We believe that Llama Guard 3 Vision serves as a good starting point to build more capable and robust content moderation tools for human-AI conversation with multimodal capabilities.