On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples
–Neural Information Processing Systems
If the relaxation is loose, however, then the resulting certificate can be too conservative to be practically useful. Recently, a less conservative robustness certificate was proposed, based on a semidefinite programming (SDP) relaxation of the ReLU activation function.
Neural Information Processing Systems
Nov-13-2025, 14:11:05 GMT
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America
- Canada (0.04)
- United States > Illinois (0.04)
- Europe > United Kingdom
- Genre:
- Research Report (0.46)
- Industry:
- Information Technology (0.46)
- Technology: