26 citations · 96 across the 33 of their papers we have counts for
4 papers · 1 filter
Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness
NhatHai Phan, Minh Vu, Yang Liu +4
In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial exam…
c-Eval: A Unified Metric to Evaluate Feature-based Explanations via Perturbation
Minh N. Vu, Truc D. Nguyen, NhatHai Phan +2
In many modern image-classification applications, understanding the cause of model's prediction can be as critical as the prediction's accuracy itself. Various feature-based local…
An Ensemble Deep Learning Model for Drug Abuse Detection in Sparse Twitter-Sphere
Han Hu, NhatHai Phan, James Geller +4
As the problem of drug abuse intensifies in the U.S., many studies that primarily utilize social media data, such as postings on Twitter, to study drug abuse-related activities use…
Scalable Differential Privacy with Certified Robustness in Adversarial Learning
NhatHai Phan, My T. Thai, Han Hu +3
In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to ad…