Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities

• URL: http://arxiv.org/abs/2506.00548v1
• Date: Sat, 31 May 2025 13:11:14 GMT
• Title: Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
• Authors: Jiahui Geng, Thy Thy Tran, Preslav Nakov, Iryna Gurevych,
• Abstract summary: Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images.<n>We exploit the capabilities of MLLMs to interpret non-textual instructions, specifically, adversarial images or audio generated by our novel method, Con Instruction.<n>Our method achieves the highest attack success rates, reaching 81.3% and 86.6% on LLaVA-v1.5 (13B)
• Score: 76.9327488986162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilities of MLLMs to interpret non-textual instructions, specifically, adversarial images or audio generated by our novel method, Con Instruction. We optimize these adversarial examples to align closely with target instructions in the embedding space, revealing the detrimental implications of MLLMs' sophisticated understanding. Unlike prior work, our method does not require training data or preprocessing of textual instructions. While these non-textual adversarial examples can effectively bypass MLLM safety mechanisms, their combination with various text inputs substantially amplifies attack success. We further introduce a new Attack Response Categorization (ARC) framework, which evaluates both the quality of the model's response and its relevance to the malicious instructions. Experimental results demonstrate that Con Instruction effectively bypasses safety mechanisms in multiple vision- and audio-language models, including LLaVA-v1.5, InternVL, Qwen-VL, and Qwen-Audio, evaluated on two standard benchmarks: AdvBench and SafeBench. Specifically, our method achieves the highest attack success rates, reaching 81.3% and 86.6% on LLaVA-v1.5 (13B). On the defense side, we explore various countermeasures against our attacks and uncover a substantial performance gap among existing techniques. Our implementation is made publicly available.

Related papers

• Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models [20.99874786089634]
  Previous jailbreak attacks often inject malicious instructions from text into less aligned modalities, such as vision.<n>We propose a novel implicit jailbreak framework termed IJA that stealthily embeds malicious instructions into images via at least significant bit steganography.<n>On commercial models like GPT-4o and Gemini-1.5 Pro, our method achieves attack success rates of over 90% using an average of only 3 queries.
  arXiv  Detail & Related papers  (2025-05-22T09:34:47Z)
• Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation [88.78166077081912]
  We introduce a multimodal unlearning benchmark, UnLOK-VQA, and an attack-and-defense framework to evaluate methods for deleting specific multimodal knowledge from MLLMs.<n>Our results show multimodal attacks outperform text- or image-only ones, and that the most effective defense removes answer information from internal model states.
  arXiv  Detail & Related papers  (2025-05-01T01:54:00Z)
• Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction [68.6543680065379]
  Large language models (LLMs) are vulnerable to prompt injection attacks.<n>We propose a novel defense method that leverages, rather than suppresses, the instruction-following abilities of LLMs.
  arXiv  Detail & Related papers  (2025-04-29T07:13:53Z)
• `Do as I say not as I do': A Semi-Automated Approach for Jailbreak Prompt Attack against Multimodal LLMs [33.49407213040455]
  We introduce the first voice-based jailbreak attack against multimodal large language models (LLMs)<n>We propose a novel strategy, in which the disallowed prompt is flanked by benign, narrative-driven prompts.<n>We demonstrate that Flanking Attack is capable of manipulating state-of-the-art LLMs into generating misaligned and forbidden outputs.
  arXiv  Detail & Related papers  (2025-02-02T10:05:08Z)
• Towards Robust Multimodal Large Language Models Against Jailbreak Attacks [24.491648943977605]
  We introduce SafeMLLM, which alternates between an attack step for generating adversarial noise and a model updating step.<n>At the attack step, SafeMLLM generates adversarial perturbations through a newly proposed contrastive embedding attack (CoE-Attack)<n>We evaluate SafeMLLM across six MLLMs and six jailbreak methods spanning multiple modalities.
  arXiv  Detail & Related papers  (2025-02-02T03:45:49Z)
• $\ extit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models [11.02754617539271]
  We introduce textitMMJ-Bench, a unified pipeline for evaluating jailbreak attacks and defense techniques for MLLMs. We assess the effectiveness of various attack methods against SoTA MLLMs and evaluate the impact of defense mechanisms on both defense effectiveness and model utility.
  arXiv  Detail & Related papers  (2024-08-16T00:18:23Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt [60.54666043358946]
  This paper introduces the Bi-Modal Adversarial Prompt Attack (BAP), which executes jailbreaks by optimizing textual and visual prompts cohesively. In particular, we utilize a large language model to analyze jailbreak failures and employ chain-of-thought reasoning to refine textual prompts.
  arXiv  Detail & Related papers  (2024-06-06T13:00:42Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings [58.82536530615557]
  We propose an Adversarial Suffix Embedding Translation Framework (ASETF) to transform continuous adversarial suffix embeddings into coherent and understandable text. Our method significantly reduces the computation time of adversarial suffixes and achieves a much better attack success rate to existing techniques.
  arXiv  Detail & Related papers  (2024-02-25T06:46:27Z)
• Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models [79.0183835295533]
  We introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities.<n>Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content.<n>We propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings.
  arXiv  Detail & Related papers  (2023-12-21T01:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.