← Search

Olive Franzese

2 accepted papers

2025

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

ICML 2025poster

Cautious predictions—where a machine learning model abstains when uncertain—are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under the guis…

2025

Secure and Confidential Certificates of Online Fairness

NeurIPS 2025poster

The "black-box service model" enables ML service providers to serve clients while keeping their intellectual property and client data confidential. Confidentiality is critical for delivering ML services legally and responsibly, but makes it difficult for outside parties to verify important model pro…

Cited by 0SourceScholar