LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses. Traditional methods rely on manual heuristics but suffer from limited generalizability. Despite being automatic, optimization-based attacks often produce unnatural prompts that can be easily detected by safety filters or require high computational costs due to discrete token optimization. In this paper, we introduce Generative Adversarial Suffix Prompter (GASP), a novel automated framework that can efficiently generate human-readable jailbreak prompts in a fully black-box setting. In particular, GASP leverages latent Bayesian optimization to craft adversarial suffixes by efficiently exploring continuous latent embedding spaces, gradually optimizing the suffix prompter to improve attack efficacy while balancing prompt coherence via a targeted iterative refinement procedure. Through comprehensive experiments, we show that GASP can produce natural adversarial prompts, significantly improving jailbreak success over baselines, reducing training times, and accelerating inference speed, thus making it an efficient and scalable solution for red-teaming LLMs. Warning: This paper contains text and examples that may be considered offensive or harmful.

Many existing jailbreak techniques rely on solving discrete combinatorial optimization, while more recent approaches involve training LLMs to generate multiple adversarial prompts. However, both approaches require significant computational resources to produce even a single adversarial prompt. We hypothesize that the inefficiency of current approaches stems from an inadequate characterization of the jailbreak problem. To address this gap, we formulate the jailbreak problem in terms of alignment. By starting from an available safety-aligned model, we leverage an unsafe reward to guide the safe model towards generating unsafe outputs using alignment techniques (e.g., reinforcement learning from human feedback), effectively performing jailbreaking via alignment. We propose a novel jailbreak method called LIAR (LeveragIng Alignment to jailbReak). To demonstrate the simplicity and effectiveness of our approach, we employ a best-of-N method to solve the alignment problem. LIAR offers significant advantages: lower computational requirements without additional training, fully black-box operation, competitive attack success rates, and more human-readable prompts. We provide theoretical insights into the possibility of jailbreaking a safety-aligned model, revealing inherent vulnerabilities in current alignment strategies for LLMs. We also provide sub-optimality guarantees for the proposed \algo. Experimentally, we achieve ASR comparable to the SoTA with a 10x improvement to perplexity and a Time-to-Attack measured in seconds rather than tens of hours.

Large Language Models (LLMs) have shown impressive proficiency across a range of natural language processing tasks yet remain vulnerable to adversarial prompts, known as jailbreak attacks, carefully designed to elicit harmful responses from LLMs. Traditional methods rely on manual heuristics, which suffer from limited generalizability. While being automatic, optimization-based attacks often produce unnatural jailbreak prompts that are easy to detect by safety filters or require high computational overhead due to discrete token optimization. Witnessing the limitations of existing jailbreak methods, we introduce Generative Adversarial Suffix Prompter (GASP), a novel framework that combines human-readable prompt generation with Latent Bayesian Optimization (LBO) to improve adversarial suffix creation in a fully black-box setting. GASP leverages LBO to craft adversarial suffixes by efficiently exploring continuous embedding spaces, gradually optimizing the model to improve attack efficacy while balancing prompt coherence through a targeted iterative refinement procedure. Our experiments show that GASP can generate natural jailbreak prompts, significantly improving attack success rates, reducing training times, and accelerating inference speed, thus making it an efficient and scalable solution for red-teaming LLMs.

While recently Large Language Models (LLMs) have achieved remarkable successes, they are vulnerable to certain jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires finding adversarial prompts that cause such jailbreaking, e.g. by appending a suffix to a given instruction, which is inefficient and time-consuming. On the other hand, automatic adversarial prompt generation often leads to semantically meaningless attacks that can easily be detected by perplexity-based filters, may require gradient information from the TargetLLM, or do not scale well due to time-consuming discrete optimization processes over the token space. In this paper, we present a novel method that uses another LLM, called the AdvPrompter, to generate human-readable adversarial prompts in seconds, $\sim800\times$ faster than existing optimization-based approaches. We train the AdvPrompter using a novel algorithm that does not require access to the gradients of the TargetLLM. This process alternates between two steps: (1) generating high-quality target adversarial suffixes by optimizing the AdvPrompter predictions, and (2) low-rank fine-tuning of the AdvPrompter with the generated adversarial suffixes. The trained AdvPrompter generates suffixes that veil the input instruction without changing its meaning, such that the TargetLLM is lured to give a harmful response. Experimental results on popular open source TargetLLMs show state-of-the-art results on the AdvBench dataset, that also transfer to closed-source black-box LLM APIs. Further, we demonstrate that by fine-tuning on a synthetic dataset generated by AdvPrompter, LLMs can be made more robust against jailbreaking attacks while maintaining performance, i.e. high MMLU scores.