175 citations · 531 across the 38 of their papers we have counts for
38 papers
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…
Differentially Private Wireless Federated Learning Using Orthogonal Sequences
Xizixiang Wei, Tianhao Wang, Ruiquan Huang +3
We propose a privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for single-input single-output (SISO) wireless federated learning (FL) systems. Fro…
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…
Practical Differentially Private and Byzantine-resilient Federated Learning
Zihang Xiang, Tianhao Wang, Wanyu Lin +1
Privacy and Byzantine resilience are two indispensable requirements for a federated learning (FL) system. Although there have been extensive studies on privacy and Byzantine securi…
GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
Josephine Lamp, Mark Derdzinski, Christopher Hannemann +4
We focus on the problem of generating high-quality, private synthetic glucose traces, a task generalizable to many other time series sources. Existing methods for time series data…
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…
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Tong Wu, Tianhao Wang, Vikash Sehwag +2
Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger pattern…
Memorization in NLP Fine-tuning Methods
Fatemehsadat Mireshghallah, Archit Uniyal, Tianhao Wang +2
Large language models are shown to present privacy risks through memorization of training data, and several recent works have studied such risks for the pre-training phase. Little…
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…
Towards More Robust Natural Language Understanding
Xinliang Frederick Zhang
Natural Language Understanding (NLU) is a branch of Natural Language Processing (NLP) that uses intelligent computer software to understand texts that encode human knowledge. Recen…
Zero-Round Active Learning
Si Chen, Tianhao Wang, Ruoxi Jia
Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: Firs…
Improving Cooperative Game Theory-based Data Valuation via Data Utility Learning
Tianhao Wang, Yu Yang, Ruoxi Jia
The Shapley value (SV) and Least core (LC) are classic methods in cooperative game theory for cost/profit sharing problems. Both methods have recently been proposed as a principled…
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…
A Unified Framework for Task-Driven Data Quality Management
Tianhao Wang, Yi Zeng, Ming Jin +1
High-quality data is critical to train performant Machine Learning (ML) models, highlighting the importance of Data Quality Management (DQM). Existing DQM schemes often cannot sati…
Differential Privacy for Text Analytics via Natural Text Sanitization
Xiang Yue, Minxin Du, Tianhao Wang +3
Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with d…
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…
One-Round Active Learning
Tianhao Wang, Si Chen, Ruoxi Jia
In this work, we initiate the study of one-round active learning, which aims to select a subset of unlabeled data points that achieve the highest model performance after being labe…
Graph Unlearning
Min Chen, Zhikun Zhang, Tianhao Wang +3
Machine unlearning is a process of removing the impact of some training data from the machine learning (ML) models upon receiving removal requests. While straightforward and legiti…
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…
PURE: A Framework for Analyzing Proximity-based Contact Tracing Protocols
Fabrizio Cicala, Weicheng Wang, Tianhao Wang +4
Many proximity-based tracing (PCT) protocols have been proposed and deployed to combat the spreading of COVID-19. In this paper, we take a systematic approach to analyze PCT protoc…