Look Closer to Your Enemy: Learning to Attack via Teacher-student Mimicking

07/27/2022
by   Mingejie Wang, et al.
0

This paper aims to generate realistic attack samples of person re-identification, ReID, by reading the enemy's mind (VM). In this paper, we propose a novel inconspicuous and controllable ReID attack baseline, LCYE, to generate adversarial query images. Concretely, LCYE first distills VM's knowledge via teacher-student memory mimicking in the proxy task. Then this knowledge prior acts as an explicit cipher conveying what is essential and realistic, believed by VM, for accurate adversarial misleading. Besides, benefiting from the multiple opposing task framework of LCYE, we further investigate the interpretability and generalization of ReID models from the view of the adversarial attack, including cross-domain adaption, cross-model consensus, and online learning process. Extensive experiments on four ReID benchmarks show that our method outperforms other state-of-the-art attackers with a large margin in white-box, black-box, and target attacks. Our code is now available at https://gitfront.io/r/user-3704489/mKXusqDT4ffr/LCYE/.

READ FULL TEXT

page 6

page 9

page 10

page 11

research
10/21/2020

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

We study the task of replicating the functionality of black-box neural m...
research
07/07/2019

A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification

Person re-identification (re-id) has made great progress in recent years...
research
03/13/2022

Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It

Transfer learning is an important approach that produces pre-trained tea...
research
03/22/2023

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition

A hard challenge in developing practical face recognition (FR) attacks i...
research
05/11/2021

Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification

Recent works show that mean-teaching is an effective framework for unsup...
research
04/08/2020

Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking

The success of DNNs has driven the extensive applications of person re-i...

Please sign up or login with your details

Forgot password? Click here to reset