A Gaussian mechanism with ε = 6 can be less private than one with ε = 8. This points to a problem with how we report privacy guarantees in machine learning. A thread 🧵
New paper at #NeurIPS2025!
"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy" in which we derive unified, tighter bounds on operational attack risks for any DP mechanisms, using f-DP.
Link: arxiv.org/abs/2507.06969
Thread👇
Continuing the thread on "Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy", for some reason it got borked.
New paper at #NeurIPS2025!
"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy" in which we derive unified, tighter bounds on operational attack risks for any DP mechanisms, using f-DP.
Link: arxiv.org/abs/2507.06969
Thread👇
New paper at #NeurIPS2025!
"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy" in which we derive unified, tighter bounds on operational attack risks for any DP mechanisms, using f-DP.
Link: arxiv.org/abs/2507.06969
Thread👇
