7 papers
Learning from Equivalence Queries, Revisited
Mark Braverman, Roi Livni, Yishay Mansour +2
Modern machine learning systems, such as generative models and recommendation systems, often evolve through a cycle of deployment, user interaction, and periodic model updates. Thi…
Protecting the Undeleted in Machine Unlearning
Aloni Cohen, Refael Kohen, Kobbi Nissim +1
Machine unlearning aims to remove specific data points from a trained model, often striving to emulate "perfect retraining", i.e., producing the model that would have been obtained…
Bayesian Perspective on Memorization and Reconstruction
Haim Kaplan, Yishay Mansour, Kobbi Nissim +1
We introduce a new Bayesian perspective on the concept of data reconstruction, and leverage this viewpoint to propose a new security definition that, in certain settings, provably…
Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems
Kobbi Nissim, Eliad Tsfadia, Chao Yan
We study the sample complexity of differentially private optimization of quasi-concave functions. For a fixed input domain , Cohen et al. (STOC 2023) proved that any g…
Data Reconstruction: When You See It and When You Don't
Edith Cohen, Haim Kaplan, Yishay Mansour +4
We revisit the fundamental question of formally defining what constitutes a reconstruction attack. While often clear from the context, our exploration reveals that a precise defini…
Credit Attribution and Stable Compression
Roi Livni, Shay Moran, Kobbi Nissim +1
Credit attribution is crucial across various fields. In academic research, proper citation acknowledges prior work and establishes original contributions. Similarly, in generative…