activity
20172022
most citedAn Ensemble Deep Learning Model for Drug Abuse Detection in Sparse Twitter-Sphere

9 citations · 9 across the 5 of their papers we have counts for

collaborators

10 papers

cs.LG2022

Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks

Khang Tran, Phung Lai, NhatHai Phan +5

Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAs), given their ability to learn joint representation from features and edges among nodes in graph dat…

cs.CR2022

User-Entity Differential Privacy in Learning Natural Language Models

Phung Lai, NhatHai Phan, Tong Sun +4

In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual dat…

cs.LG2021

Continual Learning with Differential Privacy

Pradnya Desai, Phung Lai, NhatHai Phan +1

In this paper, we focus on preserving differential privacy (DP) in continual learning (CL), in which we train ML models to learn a sequence of new tasks while memorizing previous t…

cs.CR2021

A Synergetic Attack against Neural Network Classifiers combining Backdoor and Adversarial Examples

Guanxiong Liu, Issa Khalil, Abdallah Khreishah +1

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan i…

cs.LG2020

Ontology-based Interpretable Machine Learning for Textual Data

Phung Lai, NhatHai Phan, Han Hu +3

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. D…

cs.CR2019

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…