mlsanityData to 7 Oct 2026

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models

arXiv 2412.16555 ↗First posted 21 Dec 2024cs.CLcited by 1

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

also in 1 more
Abstract (arXiv)

Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly severe. Jailbreaking attacks, as an important method for detecting vulnerabilities in LLMs, have been explored by researchers who attempt to induce these models to generate harmful content through various attack methods. Nevertheless, existing jailbreaking methods face numerous limitations, such as excessive query counts, limited coverage of jailbreak modalities, low attack success rates, and simplistic evaluation methods. To overcome these constraints, this paper proposes a multimodal jailbreaking method: JMLLM. This method integrates multiple strategies to perform comprehensive jailbreak attacks across text, visual, and auditory modalities. Additionally, we contribute a new and comprehensive dataset for multimodal jailbreaking research: TriJail, which includes jailbreak prompts for all three modalities. Experiments on the TriJail dataset and the benchmark dataset AdvBench, conducted on 13 popular LLMs, demonstrate advanced attack success rates and significant reduction in time overhead.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 76 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

25 of 76 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking21 Jun
  2. 2024Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt6 Jun
  3. 2024ImgTrojan: Jailbreaking Vision-Language Models with ONE Image5 Mar
  4. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts9 Nov

Other references · 21

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  4. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  5. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  6. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 520
  7. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreakercited by 337
  8. 2024StruQ: Defending Against Prompt Injection with Structured Queriescited by 325
  9. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 226
  10. 2024SecAlign: Defending Against Prompt Injection with Preference Optimizationcited by 179
  11. 2024Secrets of RLHF in Large Language Models Part II: Reward Modelingcited by 170
  12. 2024AdvPrompter: Fast Adaptive Adversarial Prompting for LLMscited by 146
9 more
  1. 2024Jailbreaking Attack against Multimodal Large Language Modelcited by 128
  2. 2024Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplificationcited by 80
  3. 2024Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Modelscited by 77
  4. 2024Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Charactercited by 61
  5. 2024Voice Jailbreak Attacks Against GPT-4ocited by 39
  6. 2024A Cross-Language Investigation into Jailbreak Attacks in Large Language Modelscited by 37
  7. 2024Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Stepcited by 11
  8. 2024Are You Human? An Adversarial Benchmark to Expose LLMscited by 5
  9. 2024GEGA: Graph Convolutional Networks and Evidence Retrieval Guided Attention for Enhanced Document-level Relation Extractioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024textitMMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models
  2. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
  3. 2024Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
  4. 2025Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application
  5. 2025Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
  6. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey
  7. 2026DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
  8. 2025Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency