Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks

• URL: http://arxiv.org/abs/2503.04833v2
• Date: Tue, 18 Mar 2025 07:01:13 GMT
• Title: Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks
• Authors: Liming Lu, Shuchao Pang, Siyuan Liang, Haotian Zhu, Xiyu Zeng, Aishan Liu, Yunhuai Liu, Yongbin Zhou,
• Abstract summary: We present the first adversarial training paradigm tailored to defend against jailbreak attacks during the MLLM training phase.<n>We introduce Projection Layer Against Adversarial Training (ProEAT), an end-to-end AT framework.<n>ProEAT achieves state-of-the-art defense performance, outperforming existing baselines by an average margin of +34% across text and image modalities.
• Score: 17.75247947379804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal large language models (MLLMs) have made remarkable strides in cross-modal comprehension and generation tasks. However, they remain vulnerable to jailbreak attacks, where crafted perturbations bypass security guardrails and elicit harmful outputs. In this paper, we present the first adversarial training (AT) paradigm tailored to defend against jailbreak attacks during the MLLM training phase. Extending traditional AT to this domain poses two critical challenges: efficiently tuning massive parameters and ensuring robustness against attacks across multiple modalities. To address these challenges, we introduce Projection Layer Against Adversarial Training (ProEAT), an end-to-end AT framework. ProEAT incorporates a projector-based adversarial training architecture that efficiently handles large-scale parameters while maintaining computational feasibility by focusing adversarial training on a lightweight projector layer instead of the entire model; additionally, we design a dynamic weight adjustment mechanism that optimizes the loss function's weight allocation based on task demands, streamlining the tuning process. To enhance defense performance, we propose a joint optimization strategy across visual and textual modalities, ensuring robust resistance to jailbreak attacks originating from either modality. Extensive experiments conducted on five major jailbreak attack methods across three mainstream MLLMs demonstrate the effectiveness of our approach. ProEAT achieves state-of-the-art defense performance, outperforming existing baselines by an average margin of +34% across text and image modalities, while incurring only a 1% reduction in clean accuracy. Furthermore, evaluations on real-world embodied intelligent systems highlight the practical applicability of our framework, paving the way for the development of more secure and reliable multimodal systems.

Related papers

• MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks [85.3303135160762]
  MIRAGE is a novel framework that exploits narrative-driven context and role immersion to circumvent safety mechanisms in Multimodal Large Language Models. It achieves state-of-the-art performance, improving attack success rates by up to 17.5% over the best baselines. We demonstrate that role immersion and structured semantic reconstruction can activate inherent model biases, facilitating the model's spontaneous violation of ethical safeguards.
  arXiv  Detail & Related papers  (2025-03-24T20:38:42Z)
• Adversarial Reasoning at Jailbreaking Time [49.70772424278124]
  We develop an adversarial reasoning approach to automatic jailbreaking via test-time computation. Our approach introduces a new paradigm in understanding LLM vulnerabilities, laying the foundation for the development of more robust and trustworthy AI systems.
  arXiv  Detail & Related papers  (2025-02-03T18:59:01Z)
• Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models [26.656858396343726]
  Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations.<n>Existing methods seek to mitigate these risks by applying constrained adversarial fine-tuning to CLIP vision encoders on ImageNet-scale data.<n>We explore an alternative approach of leveraging existing vision classification models that have been adversarially pre-trained on large-scale data.
  arXiv  Detail & Related papers  (2025-02-03T17:59:45Z)
• 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)
• Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs [13.317364896194903]
  We propose a two-stage adversarial tuning framework to enhance Large Language Models' generalized defense capabilities. In the first stage, we introduce the hierarchical meta-universal adversarial prompt learning to efficiently generate token-level adversarial prompts. In the second stage, we propose the automatic adversarial prompt learning to iteratively refine semantic-level adversarial prompts.
  arXiv  Detail & Related papers  (2024-06-07T15:37:15Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• Fight Back Against Jailbreaking via Prompt Adversarial Tuning [23.55544992740663]
  Large Language Models (LLMs) are susceptible to jailbreaking attacks. We propose an approach named Prompt Adversarial Tuning (PAT) that trains a prompt control attached to the user prompt as a guard prefix. Our method is effective against both grey-box and black-box attacks, reducing the success rate of advanced attacks to nearly 0%.
  arXiv  Detail & Related papers  (2024-02-09T09:09:39Z)
• Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
  We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
  arXiv  Detail & Related papers  (2023-12-20T05:06:01Z)
• Boosting Adversarial Training with Hypersphere Embedding [53.75693100495097]
  Adversarial training is one of the most effective defenses against adversarial attacks for deep learning models. In this work, we advocate incorporating the hypersphere embedding mechanism into the AT procedure. We validate our methods under a wide range of adversarial attacks on the CIFAR-10 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-02-20T08:42:29Z)

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.