Adversarial Attack via Dual-Stage Network Erosion

1 code implementation • 1 Jan 2022 • Yexin Duan, Junhua Zou, Xingyu Zhou, Wu Zhang, Jin Zhang, Zhisong Pan

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations.

Adversarial Attack

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

2 code implementations • ECCV 2020 • Junhua Zou, Zhisong Pan, Junyang Qiu, Xin Liu, Ting Rui, Wei Li

RDIM and region fitting do not require extra running time and these three steps can be well integrated into other attacks.

Diversity

Learning Coated Adversarial Camouflages for Object Detectors

no code implementations • 1 Sep 2021 • Yexin Duan, Jialin Chen, Xingyu Zhou, Junhua Zou, Zhengyun He, Jin Zhang, Wu Zhang, Zhisong Pan

An adversary can fool deep neural network object detectors by generating adversarial noises.

Object Object Detection +2

Making Adversarial Examples More Transferable and Indistinguishable

2 code implementations • 8 Jul 2020 • Junhua Zou, Yexin Duan, Boyu Li, Wu Zhang, Yu Pan, Zhisong Pan

Fast gradient sign attack series are popular methods that are used to generate adversarial examples.