LIAR: Leveraging Alignment (Best-of-N) to Jailbreak LLMs in Seconds

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.

Dual Student Networks for Data-Free Model Stealing

Existing data-free model stealing methods use a generator to produce samples in order to train a student model to match the target model outputs. To this end, the two main challenges are estimating gradients of the target model without access to its parameters, and generating a diverse set of training samples that thoroughly explores the input space. We propose a Dual Student method where two students are symmetrically trained in order to provide the generator a criterion to generate samples that the two students disagree on. On one hand, disagreement on a sample implies at least one student has classified the sample incorrectly when compared to the target model. This incentive towards disagreement implicitly encourages the generator to explore more diverse regions of the input space. On the other hand, our method utilizes gradients of student models to indirectly estimate gradients of the target model. We show that this novel training objective for the generator network is equivalent to optimizing a lower bound on the generator's loss if we had access to the target model gradients. We show that our new optimization framework provides more accurate gradient estimation of the target model and better accuracies on benchmark classification datasets. Additionally, our approach balances improved query efficiency with training computation cost. Finally, we demonstrate that our method serves as a better proxy model for transfer-based adversarial attacks than existing data-free model stealing methods.