175 citations · 531 across the 38 of their papers we have counts for
21 papers · 1 filter
Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems
Debopam Sanyal, Jui-Tse Hung, Manav Agrawal +6
Model-serving systems have become increasingly popular, especially in real-time web applications. In such systems, users send queries to the server and specify the desired performa…
White-box Membership Inference Attacks against Diffusion Models
Yan Pang, Tianhao Wang, Xuhui Kang +2
Diffusion models have begun to overshadow GANs and other generative models in industrial applications due to their superior image generation performance. The complex architecture o…
Interpreting GNN-based IDS Detections Using Provenance Graph Structural Features
Kunal Mukherjee, Joshua Wiedemeier, Tianhao Wang +4
Advanced cyber threats (e.g., Fileless Malware and Advanced Persistent Threat (APT)) have driven the adoption of provenance-based security solutions. These solutions employ Machine…
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Boyang Zhang, Xinlei He, Yun Shen +2
Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates t…
Federated Boosted Decision Trees with Differential Privacy
Samuel Maddock, Graham Cormode, Tianhao Wang +2
There is great demand for scalable, secure, and efficient privacy-preserving machine learning models that can be trained over distributed data. While deep learning models typically…
PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model
Haiming Wang, Zhikun Zhang, Tianhao Wang +4
Publishing trajectory data (individual's movement information) is very useful, but it also raises privacy concerns. To handle the privacy concern, in this paper, we apply different…
Differentially Private Vertical Federated Clustering
Zitao Li, Tianhao Wang, Ninghui Li
In many applications, multiple parties have private data regarding the same set of users but on disjoint sets of attributes, and a server wants to leverage the data to train a mode…
Using Illustrations to Communicate Differential Privacy Trust Models: An Investigation of Users' Comprehension, Perception, and Data Sharing Decision
Aiping Xiong, Chuhao Wu, Tianhao Wang +4
Proper communication is key to the adoption and implementation of differential privacy (DP). However, a prior study found that laypeople did not understand the data perturbation pr…
DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challenges
Ninghui Li, Zhikun Zhang, Tianhao Wang
We summarize the experience of participating in two differential privacy competitions organized by the National Institute of Standards and Technology (NIST). In this paper, we docu…
Concurrent Composition of Differential Privacy
Salil Vadhan, Tianhao Wang
We initiate a study of the composition properties of interactive differentially private mechanisms. An interactive differentially private mechanism is an algorithm that allows an a…
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…
Answering Multi-Dimensional Range Queries under Local Differential Privacy
Jianyu Yang, Tianhao Wang, Ninghui Li +2
In this paper, we tackle the problem of answering multi-dimensional range queries under local differential privacy. There are three key technical challenges: capturing the correlat…
Continuous Release of Data Streams under both Centralized and Local Differential Privacy
Tianhao Wang, Joann Qiongna Chen, Zhikun Zhang +5
In this paper, we study the problem of publishing a stream of real-valued data satisfying differential privacy (DP). One major challenge is that the maximal possible value can be q…
When Machine Unlearning Jeopardizes Privacy
Min Chen, Zhikun Zhang, Tianhao Wang +3
The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten r…
Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension
Aiping Xiong, Tianhao Wang, Ninghui Li +1
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments inve…
Estimating Numerical Distributions under Local Differential Privacy
Zitao Li, Tianhao Wang, Milan Lopuhaä-Zwakenberg +2
When collecting information, local differential privacy (LDP) relieves the concern of privacy leakage from users' perspective, as user's private information is randomized before se…
RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks
Tianhao Wang, Florian Kerschbaum
Watermarking of deep neural networks (DNN) can enable their tracing once released by a data owner. In this paper, we generalize white-box watermarking algorithms for DNNs, where th…
Improving Utility and Security of the Shuffler-based Differential Privacy
Tianhao Wang, Bolin Ding, Min Xu +5
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the centr…
Locally Differentially Private Frequency Estimation with Consistency
Tianhao Wang, Milan Lopuhaä-Zwakenberg, Zitao Li +2
Local Differential Privacy (LDP) protects user privacy from the data collector. LDP protocols have been increasingly deployed in the industry. A basic building block is frequency o…
Locally Differentially Private Heavy Hitter Identification
Tianhao Wang, Ninghui Li, Somesh Jha
The notion of Local Differential Privacy (LDP) enables users to answer sensitive questions while preserving their privacy. The basic LDP frequent oracle protocol enables the aggreg…
Optimizing Locally Differentially Private Protocols
Tianhao Wang, Jeremiah Blocki, Ninghui Li +1
Protocols satisfying Local Differential Privacy (LDP) enable parties to collect aggregate information about a population while protecting each user's privacy, without relying on a…