DeepAI AI Chat
Log In Sign Up

Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification

11/20/2022
by   Wenli Sun, et al.
Tongji University
Microsoft
FUDAN University
0

In recent years, person Re-identification (ReID) has rapidly progressed with wide real-world applications, but also poses significant risks of adversarial attacks. In this paper, we focus on the backdoor attack on deep ReID models. Existing backdoor attack methods follow an all-to-one/all attack scenario, where all the target classes in the test set have already been seen in the training set. However, ReID is a much more complex fine-grained open-set recognition problem, where the identities in the test set are not contained in the training set. Thus, previous backdoor attack methods for classification are not applicable for ReID. To ameliorate this issue, we propose a novel backdoor attack on deep ReID under a new all-to-unknown scenario, called Dynamic Triggers Invisible Backdoor Attack (DT-IBA). Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities. Specifically, an identity hashing network is proposed to first extract target identity information from a reference image, which is then injected into the benign images by image steganography. We extensively validate the effectiveness and stealthiness of the proposed attack on benchmark datasets, and evaluate the effectiveness of several defense methods against our attack.

READ FULL TEXT

page 1

page 3

page 6

page 7

11/29/2022

Similarity Distribution based Membership Inference Attack on Person Re-identification

While person Re-identification (Re-ID) has progressed rapidly due to its...
10/15/2020

Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing

Backdoor data poisoning is an emerging form of adversarial attack usuall...
03/04/2022

User-Level Membership Inference Attack against Metric Embedding Learning

Membership inference (MI) determines if a sample was part of a victim mo...
10/30/2019

Universal Adversarial Perturbations Against Person Re-Identification

Person re-identification (re-ID) has made great progress and achieved hi...
01/25/2022

Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation

Targeted training-set attacks inject malicious instances into the traini...
02/12/2019

A new Backdoor Attack in CNNs by training set corruption without label poisoning

Backdoor attacks against CNNs represent a new threat against deep learni...
02/20/2021

WaNet – Imperceptible Warping-based Backdoor Attack

With the thriving of deep learning and the widespread practice of using ...