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

16 citations · 68 across the 10 of their papers we have counts for

collaborators
Showing 2020Show all

2 papers · 1 filter

cs.CL2020★ 5 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.CV2020★ 8 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…