# Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

arXiv: https://arxiv.org/abs/2502.05206 · HTML: https://mlsanity.com/paper/2502.05206/

## Key facts

- Cited by 67 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 257 of its 706 references that are in the map.
- First posted on arXiv 2 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- 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 257)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)

## Built on by (most cited first, 30 of 67)

- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Measuring Agents in Production](https://mlsanity.com/paper/2512.04123/) (2025)
- [A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?](https://mlsanity.com/paper/2505.10924/) (2025)
- [A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes](https://mlsanity.com/paper/2601.05293/) (2026)
- [OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs](https://mlsanity.com/paper/2601.01592/) (2026)
- [MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety](https://mlsanity.com/paper/2602.01539/) (2026)
- [A Survey on Agentic Security: Applications, Threats and Defenses](https://mlsanity.com/paper/2510.06445/) (2025)
- [Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models](https://mlsanity.com/paper/2509.01909/) (2025)
- [Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS](https://mlsanity.com/paper/2508.03125/) (2025)
- [MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems](https://mlsanity.com/paper/2605.25002/) (2026)
- [Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers](https://mlsanity.com/paper/2505.16241/) (2025)
- [SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models](https://mlsanity.com/paper/2505.18812/) (2025)
- [AIR: Improving Agent Safety through Incident Response](https://mlsanity.com/paper/2602.11749/) (2026)
- [Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2606.10749/) (2026)
- [Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification](https://mlsanity.com/paper/2607.01793/) (2026)
- [Safeguarding LLM Agents from Misalignment through Provenance Analysis](https://mlsanity.com/paper/2607.01236/) (2026)
- [BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models](https://mlsanity.com/paper/2511.18921/) (2025)
- [TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems](https://mlsanity.com/paper/2603.15408/) (2026)
- [Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security](https://mlsanity.com/paper/2605.23989/) (2026)
- [Thought Purity: A Defense Framework For Chain-of-Thought Attack](https://mlsanity.com/paper/2507.12314/) (2025)
- [Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety](https://mlsanity.com/paper/2601.17003/) (2026)
- [Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs](https://mlsanity.com/paper/2601.21233/) (2026)
- [Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models](https://mlsanity.com/paper/2602.01025/) (2026)
- [Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents](https://mlsanity.com/paper/2605.16282/) (2026)
- [PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading](https://mlsanity.com/paper/2510.22242/) (2025)
- [DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning](https://mlsanity.com/paper/2601.20615/) (2026)
- [MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents](https://mlsanity.com/paper/2602.14281/) (2026)
- [Safety, Security, and Cognitive Risks in World Models](https://mlsanity.com/paper/2604.01346/) (2026)
- [SoK: Robustness in Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2605.05058/) (2026)

## Abstract (arXiv)

The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-powered Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models.