The Salon
The Salon
Home
People
Publications
Funding
Opportunities
Light
Dark
Automatic
Position: Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
Jie Zhang
,
Debeshee Das
,
Gautam Kamath
,
Florian Tramèr
April 2025
PDF
Cite
Type
Conference paper
Publication
Proceedings of the 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2025)
Related
Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
On the Learnability of Distribution Classes with Adaptive Adversaries
Not All Samples Are Equal: Quantifying Instance-level Difficulty in Targeted Data Poisoning
Machine Unlearning Fails to Remove Data Poisoning Attacks
Demystifying Foreground-Background Memorization in Diffusion Models
Cite
×