Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
- URL: http://arxiv.org/abs/2406.06622v1
- Date: Fri, 7 Jun 2024 15:37:15 GMT
- Title: Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
- Authors: Fan Liu, Zhao Xu, Hao Liu,
- Abstract summary: 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.
- Score: 13.317364896194903
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To enhance LLMs' generalized defense capabilities, we propose a two-stage adversarial tuning framework, which generates adversarial prompts to explore worst-case scenarios by optimizing datasets containing pairs of adversarial prompts and their safe responses. In the first stage, we introduce the hierarchical meta-universal adversarial prompt learning to efficiently and effectively generate token-level adversarial prompts. In the second stage, we propose the automatic adversarial prompt learning to iteratively refine semantic-level adversarial prompts, further enhancing LLM's defense capabilities. We conducted comprehensive experiments on three widely used jailbreak datasets, comparing our framework with six defense baselines under five representative attack scenarios. The results underscore the superiority of our proposed methods. Furthermore, our adversarial tuning framework exhibits empirical generalizability across various attack strategies and target LLMs, highlighting its potential as a transferable defense mechanism.
Related papers
- ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs [4.534938642552179]
ShieldLearner is a novel paradigm that mimics human learning in defense.
Through trial and error, it autonomously distills attack signatures into a Pattern Atlas.
Adaptive Adversarial Augmentation generates adversarial variations of successfully defended prompts.
arXiv Detail & Related papers (2025-02-16T18:47:41Z) - JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs [11.924542310342282]
We present JailPO, a novel black-box jailbreak framework to examine Large Language Models (LLMs) alignment.
For scalability and universality, JailPO meticulously trains attack models to automatically generate covert jailbreak prompts.
We also introduce a preference optimization-based attack method to enhance the jailbreak effectiveness.
arXiv Detail & Related papers (2024-12-20T07:29:10Z) - Jailbreak Attacks and Defenses Against Large Language Models: A Survey [22.392989536664288]
Large Language Models (LLMs) have performed exceptionally in various text-generative tasks.
"jailbreaking" induces the model to generate malicious responses against the usage policy and society.
We propose a comprehensive and detailed taxonomy of jailbreak attack and defense methods.
arXiv Detail & Related papers (2024-07-05T06:57:30Z) - 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) - White-box Multimodal Jailbreaks Against Large Vision-Language Models [61.97578116584653]
We propose a more comprehensive strategy that jointly attacks both text and image modalities to exploit a broader spectrum of vulnerability within Large Vision-Language Models.
Our attack method begins by optimizing an adversarial image prefix from random noise to generate diverse harmful responses in the absence of text input.
An adversarial text suffix is integrated and co-optimized with the adversarial image prefix to maximize the probability of eliciting affirmative responses to various harmful instructions.
arXiv Detail & Related papers (2024-05-28T07:13:30Z) - 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) - AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large
Language Models [55.748851471119906]
Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks.
Recent studies suggest that defending against these attacks is possible: adversarial attacks generate unlimited but unreadable gibberish prompts, detectable by perplexity-based filters.
We introduce AutoDAN, an interpretable, gradient-based adversarial attack that merges the strengths of both attack types.
arXiv Detail & Related papers (2023-10-23T17:46:07Z) - Attack Prompt Generation for Red Teaming and Defending Large Language
Models [70.157691818224]
Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content.
We propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts.
arXiv Detail & Related papers (2023-10-19T06:15:05Z) - Baseline Defenses for Adversarial Attacks Against Aligned Language
Models [109.75753454188705]
Recent work shows that text moderations can produce jailbreaking prompts that bypass defenses.
We look at three types of defenses: detection (perplexity based), input preprocessing (paraphrase and retokenization), and adversarial training.
We find that the weakness of existing discretes for text, combined with the relatively high costs of optimization, makes standard adaptive attacks more challenging for LLMs.
arXiv Detail & Related papers (2023-09-01T17:59:44Z)
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.