72 citations · 405 across the 33 of their papers we have counts for
4 papers · 1 filter
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
Hanbin Hong, Binghui Wang, Yuan Hong
We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (…
NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
Nuo Xu, Binghui Wang, Ran Ran +2
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training. In this paper, we propose…
Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
Binghui Wang, Youqi Li, Pan Zhou
Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph-based tasks such as node classification and graph classification. However, many recent works h…
GraphTrack: A Graph-based Cross-Device Tracking Framework
Binghui Wang, Tianchen Zhou, Song Li +2
Cross-device tracking has drawn growing attention from both commercial companies and the general public because of its privacy implications and applications for user profiling, per…