SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
- URL: http://arxiv.org/abs/2406.05498v1
- Date: Sat, 8 Jun 2024 15:45:31 GMT
- Title: SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
- Authors: Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, Juergen Rahmel,
- Abstract summary: This paper introduces a generic LLM jailbreak defense framework called SelfDefend.
We show that SelfDefend enables GPT-3.5 to suppress the attack success rate (ASR) by 8.97-95.74%.
We also empirically show that the tuned models are robust to targeted GCG and prompt injection attacks.
- Score: 21.414701448926614
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into four major categories: optimization-based attacks such as Greedy Coordinate Gradient (GCG), jailbreak template-based attacks such as "Do-Anything-Now", advanced indirect attacks like DrAttack, and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delay to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM defense instance to concurrently protect the target LLM instance in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs (both target and defense LLMs) have the capability to identify harmful prompts or intentions in user queries, which we empirically validate using the commonly used GPT-3.5/4 models across all major jailbreak attacks. Our measurements show that SelfDefend enables GPT-3.5 to suppress the attack success rate (ASR) by 8.97-95.74% (average: 60%) and GPT-4 by even 36.36-100% (average: 83%), while incurring negligible effects on normal queries. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. These models outperform four SOTA defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. We also empirically show that the tuned models are robust to targeted GCG and prompt injection attacks.
Related papers
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs [13.317364896194903]
Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner.
They are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs.
arXiv Detail & Related papers (2024-06-13T17:01:40Z) - AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens [83.08119913279488]
We present a systematic analysis of the dependency relationships in jailbreak attack and defense techniques.
We propose three comprehensive, automated, and logical frameworks.
We show that the proposed ensemble jailbreak attack and defense framework significantly outperforms existing research.
arXiv Detail & Related papers (2024-06-06T07:24:41Z) - Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks [59.46556573924901]
This paper introduces Defensive Prompt Patch (DPP), a novel prompt-based defense mechanism for large language models (LLMs)
Unlike previous approaches, DPP is designed to achieve a minimal Attack Success Rate (ASR) while preserving the high utility of LLMs.
Empirical results conducted on LLAMA-2-7B-Chat and Mistral-7B-Instruct-v0.2 models demonstrate the robustness and adaptability of DPP.
arXiv Detail & Related papers (2024-05-30T14:40:35Z) - LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A
Vision Paper [16.078682415975337]
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs)
This paper proposes a lightweight yet practical defense called SELFDEFEND.
It can defend against all existing jailbreak attacks with minimal delay for jailbreak prompts and negligible delay for normal user prompts.
arXiv Detail & Related papers (2024-02-24T05:34:43Z) - 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) - Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks [17.22989422489567]
Large language models (LLMs) are vulnerable to adversarial attacks or jailbreaking.
We propose an optimization-based objective for defending LLMs against jailbreaking attacks and an algorithm to create robust system-level defenses.
Our results show improved robustness to both jailbreaks seen during optimization and unknown jailbreaks, reducing the attack success rate (ASR) on GPT-4 to 6% and Llama-2 to 0% on JailbreakBench.
arXiv Detail & Related papers (2024-01-30T18:56:08Z) - Weak-to-Strong Jailbreaking on Large Language Models [96.50953637783581]
Large language models (LLMs) are vulnerable to jailbreak attacks.
Existing jailbreaking methods are computationally costly.
We propose the weak-to-strong jailbreaking attack.
arXiv Detail & Related papers (2024-01-30T18:48:37Z) - Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization [98.18718484152595]
We propose to integrate goal prioritization at both training and inference stages to counteract the intrinsic conflict between the goals of being helpful and ensuring safety.
Our work thus contributes to the comprehension of jailbreaking attacks and defenses, and sheds light on the relationship between LLMs' capability and safety.
arXiv Detail & Related papers (2023-11-15T16:42:29Z) - 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)
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.