A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination

arXiv:2608.04034 · cs.CR · Submitted 2026-08-03 · Read on arXiv

Shiji Zhao, Yuxuan Zhou, Chen Xiong, Dongxian Wu, Yang Bai, Xun Chen

cs.CR

Submitted: 2026-08-03

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• MLLMs — 36× in this paper · explained in 2 episodes
• Planner — 21× in this paper · explained in 3 episodes
• Core — 13× in this paper · explained in 2 episodes
• Attack Success Rate — 10× in this paper
• Ablation — 9× in this paper · explained in 1 episode
• Ablation Study — 6× in this paper · explained in 3 episodes
• Decoupling — 5× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 3 episodes
• Hierarchical Atomic Combination Attack — 4× in this paper
• Benchmark — 3× in this paper · explained in 2 episodes
• Composition — 3× in this paper · explained in 2 episodes
• Illegal Activities — 3× in this paper
• Vision-language models — 3× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 2× in this paper · explained in 3 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generator — 2× in this paper · explained in 2 episodes
• Hate Speech — 2× in this paper
• Malware Generation — 2× in this paper
• Papers — 2× in this paper · explained in 3 episodes
• Physical Harm — 2× in this paper
• Robustness — 2× in this paper · explained in 6 episodes
• Transferability — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 4 episodes
• Atomic Units — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 8 episodes
• Hierarchical Classification — 1× in this paper · explained in 2 episodes
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes
• Privacy Violation — 1× in this paper
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Vision Foundation Models — 1× in this paper · explained in 2 episodes

Sources

• Image Hijacks: Adversarial Images can Control Generative Models at Runtime
• ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
• InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
• FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Jailbreaking Vision-Language Models Through the Visual Modality
• Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
• Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
• TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
• X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
• Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
• The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
• MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
• AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
• Special-Character Adversarial Attacks on Open-Source Language Model
• "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
• Jailbreaking Attack against Multimodal Large Language Model
• Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
• MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills