NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
adversarial inputs
3 papers
PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation
When Are Concepts Erased From Diffusion Models?