research
∙
09/13/2023
DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
Differentially private stochastic gradient descent (DP-SGD) adds noise t...
share
research
∙
07/27/2023
The Marginal Value of Momentum for Small Learning Rate SGD
Momentum is known to accelerate the convergence of gradient descent in s...
research
∙
07/03/2023
Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems
With the emergence of large foundational models, model-serving systems a...
research
∙
06/14/2023
Differentially Private Wireless Federated Learning Using Orthogonal Sequences
We propose a novel privacy-preserving uplink over-the-air computation (A...
research
∙
06/01/2023
Interpreting GNN-based IDS Detections Using Provenance Graph Structural Features
The black-box nature of complex Neural Network (NN)-based models has hin...
research
∙
05/10/2023
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
We study multi-agent reinforcement learning in the setting of episodic M...
research
∙
04/15/2023
Practical Differentially Private and Byzantine-resilient Federated Learning
Privacy and Byzantine resilience are two indispensable requirements for ...
research
∙
03/02/2023
GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
In this paper we focus on the problem of generating high-quality, privat...
research
∙
10/06/2022
Federated Boosted Decision Trees with Differential Privacy
There is great demand for scalable, secure, and efficient privacy-preser...
research
∙
08/02/2022
Differentially Private Vertical Federated Clustering
In many applications, multiple parties have private data regarding the s...
research
∙
07/08/2022
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
As part of the effort to understand implicit bias of gradient descent in...
research
∙
07/07/2022
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
We study federated contextual linear bandits, where M agents cooperate w...
research
∙
06/27/2022
Universality of Approximate Message Passing algorithms and tensor networks
Approximate Message Passing (AMP) algorithms provide a valuable tool for...
research
∙
05/30/2022
Data Banzhaf: A Data Valuation Framework with Maximal Robustness to Learning Stochasticity
This paper studies the robustness of data valuation to noisy model perfo...
research
∙
05/25/2022
Memorization in NLP Fine-tuning Methods
Large language models are shown to present privacy risks through memoriz...
research
∙
03/07/2022
Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets
We study a Markov matching market involving a planner and a set of strat...
research
∙
02/21/2022
Using Illustrations to Communicate Differential Privacy Trust Models: An Investigation of Users' Comprehension, Perception, and Data Sharing Decision
Proper communication is key to the adoption and implementation of differ...
research
∙
12/07/2021
Locally Differentially Private Sparse Vector Aggregation
Vector mean estimation is a central primitive in federated analytics. In...
research
∙
11/24/2021
Learning to Refit for Convex Learning Problems
Machine learning (ML) models need to be frequently retrained on changing...
research
∙
10/25/2021
Learning Stochastic Shortest Path with Linear Function Approximation
We study the stochastic shortest path (SSP) problem in reinforcement lea...
research
∙
10/13/2021
What Happens after SGD Reaches Zero Loss? –A Mathematical Framework
Understanding the implicit bias of Stochastic Gradient Descent (SGD) is ...
research
∙
10/05/2021
Approximate Message Passing for orthogonally invariant ensembles: Multivariate non-linearities and spectral initialization
We study a class of Approximate Message Passing (AMP) algorithms for sym...
research
∙
07/14/2021
Zero-Round Active Learning
Active learning (AL) aims at reducing labeling effort by identifying the...
research
∙
07/13/2021
Learnability of Learning Performance and Its Application to Data Valuation
For most machine learning (ML) tasks, evaluating learning performance on...
research
∙
07/02/2021
Maximum likelihood for high-noise group orbit estimation and single-particle cryo-EM
Motivated by applications to single-particle cryo-electron microscopy (c...
research
∙
06/24/2021
DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challenges
We summarize the experience of participating in two differential privacy...
research
∙
06/22/2021
Variance-Aware Off-Policy Evaluation with Linear Function Approximation
We study the off-policy evaluation (OPE) problem in reinforcement learni...
research
∙
06/10/2021
A Unified Framework for Task-Driven Data Quality Management
High-quality data is critical to train performant Machine Learning (ML) ...
research
∙
06/02/2021
Differential Privacy for Text Analytics via Natural Text Sanitization
Texts convey sophisticated knowledge. However, texts also convey sensiti...
research
∙
05/30/2021
Concurrent Composition of Differential Privacy
We initiate a study of the composition properties of interactive differe...
research
∙
04/23/2021
One-Round Active Learning
Active learning has been a main solution for reducing data labeling cost...
research
∙
03/27/2021
Graph Unlearning
The right to be forgotten states that a data subject has the right to er...
research
∙
03/02/2021
DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Deep learning techniques have achieved remarkable performance in wide-ra...
research
∙
01/06/2021
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints
We study reinforcement learning (RL) with linear function approximation ...
research
∙
12/30/2020
PrivSyn: Differentially Private Data Synthesis
In differential privacy (DP), a challenging problem is to generate synth...
research
∙
12/17/2020
PURE: A Framework for Analyzing Proximity-based Contact Tracing Protocols
Many proximity-based tracing (PCT) protocols have been proposed and depl...
research
∙
10/23/2020
Analysis and Verification of Relation between Digitizer's Sampling Properties and Energy Resolution of HPGe Detectors
The CDEX (China Dark matter Experiment) aims at detection of WIMPs (Weak...
research
∙
09/14/2020
Answering Multi-Dimensional Range Queries under Local Differential Privacy
In this paper, we tackle the problem of answering multi-dimensional rang...
research
∙
09/14/2020
A Principled Approach to Data Valuation for Federated Learning
Federated learning (FL) is a popular technique to train machine learning...
research
∙
09/11/2020
Improving Robustness to Model Inversion Attacks via Mutual Information Regularization
This paper studies defense mechanisms against model inversion (MI) attac...
research
∙
05/24/2020
Continuous Release of Data Streams under both Centralized and Local Differential Privacy
In this paper, we study the problem of publishing a stream of real-value...
research
∙
05/05/2020
When Machine Unlearning Jeopardizes Privacy
The right to be forgotten states that a data owner has the right to eras...
research
∙
03/31/2020
Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model
We study the non-convex optimization landscape for maximum likelihood es...
research
∙
03/31/2020
Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension
Differential privacy protects an individual's privacy by perturbing data...
research
∙
12/02/2019
Estimating Numerical Distributions under Local Differential Privacy
When collecting information, local differential privacy (LDP) relieves t...
research
∙
10/31/2019
Robust and Undetectable White-Box Watermarks for Deep Neural Networks
Training deep neural networks (DNN) is expensive in terms of computation...
research
∙
08/30/2019
MURS: Practical and Robust Privacy Amplification with Multi-Party Differential Privacy
When collecting information, local differential privacy (LDP) alleviates...
research
∙
08/30/2019
Practical and Robust Privacy Amplification with Multi-Party Differential Privacy
When collecting information, local differential privacy (LDP) alleviates...
research
∙
05/20/2019