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

Zhaorun Chen, Xun Liu, Mintong Kang, Jiawei Zhang, Minzhou Pan, Shuang Yang, Bo Li

Keywords: multi-modal red-teaming, multi-modal alignment, agent, safety, adversarial robustness

TL;DR: We propose ARMs, an novel agentic multimodal red-teaming framework that optimizes 17 attack strategies to provide comprehensive risk assessment, and build ARMs-Bench, comprising 30K red-teaming instances to guide safer multimodal alignment.

Abstract: 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 adversarial strategies. 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. This is the first red teaming framework that provides controllable generation given risk definitions. 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 with ARMs. To balance the diversity and effectiveness of the attack, we design a layered memory with an epsilon-greedy attack algorithm. Extensive experiments on different instance-based benchmarks and policy-based safety evaluations show that ARMs achieves the state-of-the-art attack success rate (ASR), improving ASR by an average of 52.1% compared to existing baselines and even exceeding 90% ASR on Claude-4-Sonnet, a constitutionally-aligned model widely recognized for its robustness. 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 benchmark comprising 30K red-teaming instances spanning 51 diverse risk categories, grounded in both real-world multimodal threats and regulatory risks. Fine-tuning with ARMs-Bench substantially reduces ASR while preserving general utility of VLMs, providing actionable insights to improve multimodal safety alignment.

Submission Number: 67