activity
20182022
most citedPoison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networks

16 citations · 51 across the 6 of their papers we have counts for

collaborators

8 papers

cs.LG2022

How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?

Alvin Chan, Yew-Soon Ong, Clement Tan

Model robustness is vital for the reliable deployment of machine learning models in real-world applications. Recent studies have shown that data augmentation can result in model ov…

cs.AI202210 cited

A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges

Zhenghua Chen, Min Wu, Alvin Chan +2

Artificial Intelligence (AI) is a fast-growing research and development (R&D) discipline which is attracting increasing attention because of its promises to bring vast benefits for…

cs.LG202112 cited

Deep Extrapolation for Attribute-Enhanced Generation

Alvin Chan, Ali Madani, Ben Krause +1

Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequen…

cs.CL20205 cited

Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder

Alvin Chan, Yi Tay, Yew-Soon Ong +1

This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a 'backdoor poisoning' attack on NLP…

cs.CV20208 cited

Jacobian Adversarially Regularized Networks for Robustness

Alvin Chan, Yi Tay, Yew Soon Ong +1

Adversarial examples are crafted with imperceptible perturbations with the intent to fool neural networks. Against such attacks, adversarial training and its variants stand as the…

cs.LG2019

What it Thinks is Important is Important: Robustness Transfers through Input Gradients

Alvin Chan, Yi Tay, Yew-Soon Ong

Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations a…