Zhixing Ye

most citedDominant Patterns: Critical Features Hidden in Deep Neural Networks

2 citations · 2 across the 3 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2021★ 2 cited

Dominant Patterns: Critical Features Hidden in Deep Neural Networks

Zhixing Ye, Shaofei Qin, Sizhe Chen +1

In this paper, we find the existence of critical features hidden in Deep NeuralNetworks (DNNs), which are imperceptible but can actually dominate the outputof DNNs. We call these f…

cs.LG2021

Measuring the Transferability of $ℓ_{\infty}$ Attacks by the $ℓ_{2}$ Norm

Sizhe Chen, Qinghua Tao, Zhixing Ye +1

Deep neural networks could be fooled by adversarial examples with trivial differences to original samples. To keep the difference imperceptible in human eyes, researchers bound the…

Dominant Patterns: Critical Features Hidden in Deep Neural Networks

Measuring the Transferability of ℓ∞​ Attacks by the ℓ2​ Norm

Measuring the Transferability of $ℓ_{\infty}$ Attacks by the $ℓ_{2}$ Norm