James Beetham

James Beetham, Navid Kardan, Ajmal Mian et al.

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.

James Beetham, Souradip Chakraborty, Mengdi Wang et al.

Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or trained adversarial generators, but are slow, compute-intensive, and often impractical. We argue that these inefficiencies stem from a mischaracterization of the problem. Instead, we frame jailbreaks as inference-time misalignment and introduce LIAR (Leveraging Inference-time misAlignment to jailbReak), a fast, black-box, best-of-$N$ sampling attack requiring no training. LIAR matches state-of-the-art success rates while reducing perplexity by $10\times$ and Time-to-Attack from hours to seconds. We also introduce a theoretical "safety net against jailbreaks" metric to quantify safety alignment strength and derive suboptimality bounds. Our work offers a simple yet effective tool for evaluating LLM robustness and advancing alignment research.