35 citations · 155 across the 31 of their papers we have counts for
8 papers · 1 filter
Explain2Attack: Text Adversarial Attacks via Cross-Domain Interpretability
Mahmoud Hossam, Trung Le, He Zhao +1
Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that loo…
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks
He Zhao, Thanh Nguyen, Trung Le +4
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Many advers…
Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness
Anh Bui, Trung Le, He Zhao +4
Ensemble-based adversarial training is a principled approach to achieve robustness against adversarial attacks. An important technique of this approach is to control the transferab…
Neural Topic Model via Optimal Transport
He Zhao, Dinh Phung, Viet Huynh +2
Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis. However, it…
MED-TEX: Transferring and Explaining Knowledge with Less Data from Pretrained Medical Imaging Models
Thanh Nguyen-Duc, He Zhao, Jianfei Cai +1
Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation f…
SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression
Jinming Zhao, Ming Liu, Longxiang Gao +5
Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this pa…
Improving Adversarial Robustness by Enforcing Local and Global Compactness
Anh Bui, Trung Le, He Zhao +4
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defens…
Leveraging Cross Feedback of User and Item Embeddings with Attention for Variational Autoencoder based Collaborative Filtering
Yuan Jin, He Zhao, Ming Liu +5
Matrix factorization (MF) has been widely applied to collaborative filtering in recommendation systems. Its Bayesian variants can derive posterior distributions of user and item em…