133 citations · 187 across the 13 of their papers we have counts for
13 papers
Why Is Public Pretraining Necessary for Private Model Training?
Arun Ganesh, Mahdi Haghifam, Milad Nasr +5
In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported with the use of pretraining on publicly…
Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees
Banghua Zhu, Lun Wang, Qi Pang +4
We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence a…
FED-: Privacy Preserving Federated Correlation Test
Lun Wang, Qi Pang, Shuai Wang +1
In this paper, we propose the first secure federated -test protocol Fed-. To minimize both the privacy leakage and the communication cost, we recast -test to the sec…
Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space
Lun Wang, Iosif Pinelis, Dawn Song
We prove that sketch, a well-celebrated streaming algorithm for frequency moments estimation, is differentially private as is when . sketc…
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Lun Wang, Zaynah Javed, Xian Wu +3
Recent research has confirmed the feasibility of backdoor attacks in deep reinforcement learning (RL) systems. However, the existing attacks require the ability to arbitrarily modi…
DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Wenxiao Wang, Tianhao Wang, Lun Wang +4
Deep learning techniques have achieved remarkable performance in wide-ranging tasks. However, when trained on privacy-sensitive datasets, the model parameters may expose private in…
PrivFramework: A System for Configurable and Automated Privacy Policy Compliance
Usmann Khan, Lun Wang, Jithendaraa Subramanian +2
Today's massive scale of data collection coupled with recent surges of consumer data leaks has led to increased attention towards data privacy and related risks. Conventional data…
Towards Bidirectional Protection in Federated Learning
Lun Wang, Qi Pang, Shuai Wang +1
Prior efforts in enhancing federated learning (FL) security fall into two categories. At one end of the spectrum, some work uses secure aggregation techniques to hide the individua…
Towards practical differentially private causal graph discovery
Lun Wang, Qi Pang, Dawn Song
Causal graph discovery refers to the process of discovering causal relation graphs from purely observational data. Like other statistical data, a causal graph might leak sensitive…
D2P-Fed: Differentially Private Federated Learning With Efficient Communication
Lun Wang, Ruoxi Jia, Dawn Song
In this paper, we propose the discrete Gaussian based differentially private federated learning (D2P-Fed), a unified scheme to achieve both differential privacy (DP) and communicat…
Duet: An Expressive Higher-order Language and Linear Type System for Statically Enforcing Differential Privacy
Joseph P. Near, David Darais, Chike Abuah +8
During the past decade, differential privacy has become the gold standard for protecting the privacy of individuals. However, verifying that a particular program provides different…
Data Capsule: A New Paradigm for Automatic Compliance with Data Privacy Regulations
Lun Wang, Joseph P. Near, Neel Somani +4
The increasing pace of data collection has led to increasing awareness of privacy risks, resulting in new data privacy regulations like General data Protection Regulation (GDPR). S…
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Wenbo Guo, Lun Wang, Xinyu Xing +2
A trojan backdoor is a hidden pattern typically implanted in a deep neural network. It could be activated and thus forces that infected model behaving abnormally only when an input…