Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems

תקציר מקורי באנגליתarXiv:2607.23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation. Existing falsification approaches rely on conditional sampling strategies that factor the joint distribution over environments and system executions, and therefore suffer from multiplicative rarity effects: the simultaneous scarcity of failure-inducing inputs and failure-inducing traces makes exhaustive search prohibitively expensive. This paper develops DiffTilt, a distributional framework that exponentially tilts a diffusion model-induced joint distribution over environments and executions. We show that diffusion-guided sampling admits an exact interpretation as importance sampling in the joint space,