Catuscia Palamidessi

Systems with near-perfect EER can still expose significant privacy vulnerabilities, with worst-case disclosures effectively doubling an attacker's success rate.

Forget epsilon-only comparisons: a QIF lens reveals that some "optimal" LDP protocols are actually weaker than you thought.

Standard shuffling in federated learning doesn't stop source inference attacks, but parameter-level shuffling with residue number systems does, without hurting accuracy.