AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs

• URL: http://arxiv.org/abs/2404.07921v3
• Date: Sun, 24 Nov 2024 18:03:43 GMT
• Title: AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs
• Authors: Zeyi Liao, Huan Sun,
• Abstract summary: GCGcitepzou2023universal proposes a discrete token optimization algorithm and selects the single suffix with the lowest loss to successfully jailbreak aligned LLMs. We utilize successful suffixes as training data to learn a generative model, named AmpleGCG, which captures the distribution of adversarial suffixes given a harmful query. A AmpleGCG model can generate 200 adversarial suffixes for one harmful query in only 4 seconds, rendering it more challenging to defend.
• Score: 11.094625711201648
• License:
• Abstract: As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety alignment, recent work GCG~\citep{zou2023universal} proposes a discrete token optimization algorithm and selects the single suffix with the lowest loss to successfully jailbreak aligned LLMs. In this work, we first discuss the drawbacks of solely picking the suffix with the lowest loss during GCG optimization for jailbreaking and uncover the missed successful suffixes during the intermediate steps. Moreover, we utilize those successful suffixes as training data to learn a generative model, named AmpleGCG, which captures the distribution of adversarial suffixes given a harmful query and enables the rapid generation of hundreds of suffixes for any harmful queries in seconds. AmpleGCG achieves near 100\% attack success rate (ASR) on two aligned LLMs (Llama-2-7B-chat and Vicuna-7B), surpassing two strongest attack baselines. More interestingly, AmpleGCG also transfers seamlessly to attack different models, including closed-source LLMs, achieving a 99\% ASR on the latest GPT-3.5. To summarize, our work amplifies the impact of GCG by training a generative model of adversarial suffixes that is universal to any harmful queries and transferable from attacking open-source LLMs to closed-source LLMs. In addition, it can generate 200 adversarial suffixes for one harmful query in only 4 seconds, rendering it more challenging to defend.

Related papers

• LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs [13.36946005380889]
  We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Our method significantly outperforms existing red-teaming approaches, achieving a +57.2% improvement in Attack Success Rate (ASR) on LLaMA2-7B-chat and a +50.3% increase on Claude 2.
  arXiv  Detail & Related papers  (2024-11-13T18:44:30Z)
• AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts [10.536276489213497]
  A generative model can quickly produce numerous customizable gibberish adversarial suffixes for any harmful query. We introduce AmpleGCG-Plus, an enhanced version that achieves better performance in fewer attempts. We jailbreak the newer GPT-4o series of models at similar rates to GPT-4, and, uncovers vulnerabilities against the recently proposed circuit breakers defense.
  arXiv  Detail & Related papers  (2024-10-29T15:40:07Z)
• Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities [63.603861880022954]
  We introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability. Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs. It exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3.
  arXiv  Detail & Related papers  (2024-10-24T06:36:12Z)
• Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models [16.938267820586024]
  We propose Faster-GCG, an efficient adversarial jailbreak method by delving deep into the design of GCG. Experiments demonstrate that Faster-GCG can surpass the original GCG with only 1/10 of the computational cost.
  arXiv  Detail & Related papers  (2024-10-20T11:27:41Z)
• 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)
• Improved Techniques for Optimization-Based Jailbreaking on Large Language Models [78.32176751215073]
  Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. We present several improved (empirical) techniques for optimization-based jailbreaks like GCG. The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate.
  arXiv  Detail & Related papers  (2024-05-31T17:07:15Z)
• Improved Generation of Adversarial Examples Against Safety-aligned LLMs [72.38072942860309]
  Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks. We show that 87% of the query-specific adversarial suffixes generated by the developed combination can induce Llama-2-7B-Chat to produce the output that exactly matches the target string on AdvBench.
  arXiv  Detail & Related papers  (2024-05-28T06:10:12Z)
• PAL: Proxy-Guided Black-Box Attack on Large Language Models [55.57987172146731]
  Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated capabilities to generate harmful content when manipulated. We introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. Our attack achieves 84% attack success rate (ASR) on GPT-3.5-Turbo and 48% on Llama-2-7B, compared to 4% for the current state of the art.
  arXiv  Detail & Related papers  (2024-02-15T02:54:49Z)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [99.23352758320945]
  We propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on large language models (LLMs) Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs.
  arXiv  Detail & Related papers  (2023-10-05T17:01:53Z)
• Universal and Transferable Adversarial Attacks on Aligned Language Models [118.41733208825278]
  We propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable.
  arXiv  Detail & Related papers  (2023-07-27T17:49:12Z)

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.