Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

• URL: http://arxiv.org/abs/2405.09113v1
• Date: Wed, 15 May 2024 06:11:24 GMT
• Title: Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
• Authors: Kai Hu, Weichen Yu, Tianjun Yao, Xiang Li, Wenhe Liu, Lijun Yu, Yining Li, Kai Chen, Zhiqiang Shen, Matt Fredrikson,
• Abstract summary: Large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive-to-Sparse Constrained Optimization (ADC), which effectively jailbreaks several open-source LLMs.
• Score: 46.98249466236357
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained Optimization (ADC), which effectively jailbreaks several open-source LLMs. Our approach relaxes the discrete jailbreak optimization into a continuous optimization and progressively increases the sparsity of the optimizing vectors. Consequently, our method effectively bridges the gap between discrete and continuous space optimization. Experimental results demonstrate that our method is more effective and efficient than existing token-level methods. On Harmbench, our method achieves state of the art attack success rate on seven out of eight LLMs. Code will be made available. Trigger Warning: This paper contains model behavior that can be offensive in nature.

Related papers

• Adversarial Attacks on Large Language Models Using Regularized Relaxation [1.042748558542389]
  Large Language Models (LLMs) are used for numerous practical applications. adversarial attack methods are extensively used to study and understand these vulnerabilities. We propose a novel technique for adversarial attacks that overcomes these limitations by leveraging regularized gradients with continuous optimization methods.
  arXiv  Detail & Related papers  (2024-10-24T21:01:45Z)
• Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks [24.935016443423233]
  This study introduces a novel optimization approach, termed the emphfunctional homotopy method. By constructing a series of easy-to-hard optimization problems, we iteratively solve these problems using principles derived from established homotopy methods. We apply this approach to jailbreak attack synthesis for large language models (LLMs), achieving a $20%-30%$ improvement in success rate over existing methods.
  arXiv  Detail & Related papers  (2024-10-05T17:22:39Z)
• AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs [34.221522224051846]
  We propose an adaptive position pre-fill jailbreak attack approach for executing jailbreak attacks on Large Language Models (LLMs) Our method leverages the model's instruction-following capabilities to first output safe content, then exploits its narrative-shifting abilities to generate harmful content. Our method can improve the attack success rate by 47% on the widely recognized secure model (Llama2) compared to existing approaches.
  arXiv  Detail & Related papers  (2024-09-11T00:00:58Z)
• Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer [33.67942887761857]
  We present ECLIPSE, a novel and efficient black-box jailbreaking method utilizing optimizable suffixes. We employ task prompts to translate jailbreaking goals into natural language instructions, which guides the LLM to generate adversarial suffixes for malicious queries. ECLIPSE achieves an average attack success rate (ASR) of 0.92 across three open-source LLMs and GPT-3.5-Turbo, significantly surpassing GCG in 2.4 times.
  arXiv  Detail & Related papers  (2024-08-21T03:35:24Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• Two Optimizers Are Better Than One: LLM Catalyst Empowers Gradient-Based Optimization for Prompt Tuning [69.95292905263393]
  We show that gradient-based optimization and large language models (MsLL) are complementary to each other, suggesting a collaborative optimization approach. Our code is released at https://www.guozix.com/guozix/LLM-catalyst.
  arXiv  Detail & Related papers  (2024-05-30T06:24:14Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• Attacking Large Language Models with Projected Gradient Descent [12.130638442765857]
  Projected Gradient Descent (PGD) for adversarial prompts is up to one order of magnitude faster than state-of-the-art discrete optimization. Our PGD for LLMs is up to one order of magnitude faster than state-of-the-art discrete optimization to achieve the same devastating attack results.
  arXiv  Detail & Related papers  (2024-02-14T13:13:26Z)

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.