ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
cs.AI, cs.LG
Submitted: 2025-10-03
Updated: 2026-11-04
Comments: Accepted to ICLR 2026. Distinguished Paper Award at the CVPR 2026 AdvML Workshop. 64 pages, 16 figures. Project page: https://arms-redteaming-agent.github.io
Journal ref: The Fourteenth International Conference on Learning Representations (ICLR 2026)
Project page: https://arms-redteaming-agent.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Can Editing LLMs Inject Harm?
- Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
- How Robust is Google's Bard to Adversarial Image Attacks?
- Explaining and Harnessing Adversarial Examples
- OpenAI o1 System Card
- Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
- Red Teaming Visual Language Models
- Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
- JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Jailbreaking Attack against Multimodal Large Language Model
- Red Teaming Language Models with Language Models
- Safety Alignment Should Be Made More Than Just a Few Tokens Deep
- X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
- Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- Manipulating Multimodal Agents via Cross-Modal Prompt Injection
- Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis
- Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents