2 papers
cs.AI2026
Bounding the Black Box: A Statistical Certification Framework for AI Risk Regulation
Natan Levy, Gadi Perl
Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: th…
cs.LG2025
Beyond Benchmarks: On The False Promise of AI Regulation
Gabriel Stanovsky, Renana Keydar, Gadi Perl +1
The performance of AI models on safety benchmarks does not indicate their real-world performance after deployment. This opaqueness of AI models impedes existing regulatory framewor…