# ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

arXiv: https://arxiv.org/abs/2510.02677 · HTML: https://mlsanity.com/paper/2510.02677/

## Key facts

- Cited by 5 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 24 of its 50 references that are in the map.
- First posted on arXiv 3 Oct 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 / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 24 of 24)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Safety Alignment Should Be Made More Than Just a Few Tokens Deep](https://mlsanity.com/paper/2406.05946/) (2024)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [How Robust is Google's Bard to Adversarial Image Attacks?](https://mlsanity.com/paper/2309.11751/) (2023)
- [Jailbreaking Attack against Multimodal Large Language Model](https://mlsanity.com/paper/2402.02309/) (2024)
- [X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents](https://mlsanity.com/paper/2504.13203/) (2025)
- [Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt](https://mlsanity.com/paper/2406.04031/) (2024)
- [Red Teaming Visual Language Models](https://mlsanity.com/paper/2401.12915/) (2024)
- [Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency](https://mlsanity.com/paper/2501.04931/) (2025)
- [Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis](https://mlsanity.com/paper/2503.20047/) (2025)
- [Manipulating Multimodal Agents via Cross-Modal Prompt Injection](https://mlsanity.com/paper/2504.14348/) (2025)
- [AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration](https://mlsanity.com/paper/2503.15754/) (2025)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts](https://mlsanity.com/paper/2502.21059/) (2025)
- [Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset](https://mlsanity.com/paper/2506.19054/) (2025)
- [Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation](https://mlsanity.com/paper/2503.06254/) (2025)
- [Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models](https://mlsanity.com/paper/2411.11496/) (2024)
- [Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application](https://mlsanity.com/paper/2503.06989/) (2025)

## Built on by (most cited first, 5 of 5)

- [DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents](https://mlsanity.com/paper/2605.04808/) (2026)
- [A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applications](https://mlsanity.com/paper/2602.21267/) (2026)
- [DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs](https://mlsanity.com/paper/2607.11228/) (2026)
- [A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination](https://mlsanity.com/paper/2608.04034/) (2026)
- [DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models](https://mlsanity.com/paper/2609.05525/) (2026)

## Abstract (arXiv)

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow set of adversarial patterns or depend heavily on manual engineering, lacking scalable exploration of emerging real-world VLM vulnerabilities. To bridge this gap, we propose ARMs, an adaptive red-teaming agent that systematically conducts comprehensive risk assessments for VLMs. Given a target harmful behavior or risk definition, ARMs automatically optimizes diverse red-teaming strategies with reasoning-enhanced multi-step orchestration, to effectively elicit harmful outputs from target VLMs. We propose 11 novel multimodal attack strategies, covering diverse adversarial patterns of VLMs (e.g., reasoning hijacking, contextual cloaking), and integrate 17 red-teaming algorithms into ARMs via model context protocol (MCP). To balance the diversity and effectiveness of the attack, we design a layered memory with an epsilon-greedy attack exploration algorithm. Extensive experiments on instance- and policy-based benchmarks show that ARMs achieves SOTA attack success rates, exceeding baselines by an average of 52.1% and surpassing 90% on Claude-4-Sonnet. We show that the diversity of red-teaming instances generated by ARMs is significantly higher, revealing emerging vulnerabilities in VLMs. Leveraging ARMs, we construct ARMs-Bench, a large-scale multimodal safety dataset comprising over 30K red-teaming instances spanning 51 diverse risk categories, grounded in both real-world multimodal threats and regulatory risks. Safety fine-tuning with ARMs-Bench substantially improves the robustness of VLMs while preserving their general utility, providing actionable guidance to improve multimodal safety alignment against emerging threats.