23 citations · 58 across the 9 of their papers we have counts for
7 papers · 1 filter
Observational Auditing of Label Privacy
Iden Kalemaj, Luca Melis, Maxime Boucher +2
Differential privacy (DP) auditing is essential for evaluating privacy guarantees in machine learning systems. Existing auditing methods, however, pose a significant challenge for…
BLIA: Detect model memorization in binary classification model through passive Label Inference attack
Mohammad Wahiduzzaman Khan, Sheng Chen, Ilya Mironov +2
Model memorization has implications for both the generalization capacity of machine learning models and the privacy of their training data. This paper investigates label memorizati…
Green Federated Learning
Ashkan Yousefpour, Shen Guo, Ashish Shenoy +7
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets. As a consequence, the amount of compute used in trainin…
Reconciling Security and Communication Efficiency in Federated Learning
Karthik Prasad, Sayan Ghosh, Graham Cormode +3
Cross-device Federated Learning is an increasingly popular machine learning setting to train a model by leveraging a large population of client devices with high privacy and securi…
Defending against Reconstruction Attacks with Rényi Differential Privacy
Pierre Stock, Igor Shilov, Ilya Mironov +1
Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can…
Opacus: User-Friendly Differential Privacy Library in PyTorch
Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles +9
We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus.ai). Opacus is designed for simplicity, flexi…
Antipodes of Label Differential Privacy: PATE and ALIBI
Mani Malek, Ilya Mironov, Karthik Prasad +2
We consider the privacy-preserving machine learning (ML) setting where the trained model must satisfy differential privacy (DP) with respect to the labels of the training examples.…