182 citations · 625 across the 44 of their papers we have counts for
9 papers · 1 filter
A Randomized Approach for Tight Privacy Accounting
Jiachen T. Wang, Saeed Mahloujifar, Tong Wu +2
Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). The privacy parameter ($\eps$ or ) is often easy to estima…
Private Data Valuation and Fair Payment in Data Marketplaces
Zhihua Tian, Jian Liu, Jingyu Li +5
Data valuation is an essential task in a data marketplace. It aims at fairly compensating data owners for their contribution. There is increasing recognition in the machine learnin…
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
Yi Zeng, Minzhou Pan, Himanshu Jahagirdar +3
Given the volume of data needed to train modern machine learning models, external suppliers are increasingly used. However, incorporating external data poses data poisoning risks,…
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks
Xuanli He, Qiongkai Xu, Yi Zeng +4
Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generation APIs, a recent…
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang +2
Propose-Test-Release (PTR) is a differential privacy framework that works with local sensitivity of functions, instead of their global sensitivity. This framework is typically used…
Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
Yi Zeng, Minzhou Pan, Hoang Anh Just +3
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware spe…
Improving Robustness to Model Inversion Attacks via Mutual Information Regularization
Tianhao Wang, Yuheng Zhang, Ruoxi Jia
This paper studies defense mechanisms against model inversion (MI) attacks -- a type of privacy attacks aimed at inferring information about the training data distribution given th…
REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data
Xinyun Chen, Wenxiao Wang, Chris Bender +4
Training deep neural networks from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to pro…
Privacy-Enhanced Architecture for Occupancy-based HVAC Control
Ruoxi Jia, Roy Dong, S. Shankar Sastry +1
Large-scale sensing and actuation infrastructures have allowed buildings to achieve significant energy savings; at the same time, these technologies introduce significant privacy r…