← Search

Tudor Ioan Cebere

2 accepted papers

2025

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

ICLR 2025poster

Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD. In this work, we focus on a threat model where the adversary has access only to the final model, with no visibility into intermediate updates. In the literature, this ``hidden…

Cited by 12SourcePDFScholar
2024

Confidential-DPproof: Confidential Proof of Differentially Private Training

ICLR 2024spotlight

Post hoc privacy auditing techniques can be used to test the privacy guarantees of a model, but come with several limitations: (i) they can only establish lower bounds on the privacy loss, (ii) the intermediate model updates and some data must be shared with the auditor to get a better approximation…

Cited by 5SourcePDFScholar