3 citations · 7 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022★ 3 cited
Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples
Hui Liu, Bo Zhao, Kehuan Zhang +1
Although deep neural networks (DNNs) have shown impressive performance on many perceptual tasks, they are vulnerable to adversarial examples that are generated by adding slight but…
cs.LG2021★ 3 cited
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features
Hui Liu, Bo Zhao, Minzhi Ji +3
Deep neural networks (DNNs) are under threat from adversarial example attacks. The adversary can easily change the outputs of DNNs by adding small well-designed perturbations to in…
cs.LG2020
GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial Attack
Hui Liu, Bo Zhao, Minzhi Ji +1
Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs). Exis…