PolicyShiftGuard-3B

Papers using or citing this model 1

• PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails · 2026 · arXiv

  Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Real deployments are different: the same image may be allowed in one product, restricted...