Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed without injection to exponential growth with the number of inference-time samples. We first identify a minimal statistical mechanism for these two regimes by giving a small set of assumptions on the distribution of safe generation across contexts under which both scaling laws follow. To explain this phenomenon further, we propose a theoretical generative model of proxy language in terms of a spin-glass system operating in a replica-symmetry-breaking regime,...
| Authors | Indranil Halder, Annesya Banerjee, Cengiz Pehlevan |
|---|---|
| Primary category | cs.LG |
| Published | 11 March 2026 |
| Last updated at source | 8 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.