311 citations · 601 across the 23 of their papers we have counts for
14 papers · 1 filter
Multi-Task Differential Privacy Under Distribution Skew
Walid Krichene, Prateek Jain, Shuang Song +3
We study the problem of multi-task learning under user-level differential privacy, in which users contribute data to tasks, each involving a subset of users. One important…
Measuring Forgetting of Memorized Training Examples
Matthew Jagielski, Om Thakkar, Florian Tramèr +8
Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific trainin…
Debugging Differential Privacy: A Case Study for Privacy Auditing
Florian Tramer, Andreas Terzis, Thomas Steinke +3
Differential Privacy can provide provable privacy guarantees for training data in machine learning. However, the presence of proofs does not preclude the presence of errors. Inspir…
Toward Training at ImageNet Scale with Differential Privacy
Alexey Kurakin, Shuang Song, Steve Chien +3
Differential privacy (DP) is the de facto standard for training machine learning (ML) models, including neural networks, while ensuring the privacy of individual examples in the tr…
Public Data-Assisted Mirror Descent for Private Model Training
Ehsan Amid, Arun Ganesh, Rajiv Mathews +6
In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training. (Here, public d…
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
Steve Chien, Prateek Jain, Walid Krichene +4
We study the problem of differentially private (DP) matrix completion under user-level privacy. We design a joint differentially private variant of the popular Alternating-Least-Sq…
Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning
Milad Nasr, Shuang Song, Abhradeep Thakurta +2
Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, wh…
Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels
Shuang Song, David Berthelot, Afshin Rostamizadeh
We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of…
That which we call private
Úlfar Erlingsson, Ilya Mironov, Ananth Raghunathan +1
The guarantees of security and privacy defenses are often strengthened by relaxing the assumptions made about attackers or the context in which defenses are deployed. Such relaxati…
Rényi Differential Privacy Mechanisms for Posterior Sampling
Joseph Geumlek, Shuang Song, Kamalika Chaudhuri
Using a recently proposed privacy definition of Rényi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We…
Composition Properties of Inferential Privacy for Time-Series Data
Shuang Song, Kamalika Chaudhuri
With the proliferation of mobile devices and the internet of things, developing principled solutions for privacy in time series applications has become increasingly important. Whil…
Pufferfish Privacy Mechanisms for Correlated Data
Shuang Song, Yizhen Wang, Kamalika Chaudhuri
Many modern databases include personal and sensitive correlated data, such as private information on users connected together in a social network, and measurements of physical acti…
Learning from Data with Heterogeneous Noise using SGD
Shuang Song, Kamalika Chaudhuri, Anand D. Sarwate
We consider learning from data of variable quality that may be obtained from different heterogeneous sources. Addressing learning from heterogeneous data in its full generality is…
The Large Margin Mechanism for Differentially Private Maximization
Kamalika Chaudhuri, Daniel Hsu, Shuang Song
A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a dat…