Robust Backdoor Attacks against Deep Neural Networks in Real Physical World

by   Mingfu Xue, et al.

Deep neural networks (DNN) have been widely deployed in various practical applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the malicious behaviors by submitting specific backdoor instance. However, almost all the existing backdoor works focused on the digital domain, while few studies investigate the backdoor attacks in real physical world. Restricted to a variety of physical constrains, the performance of backdoor attacks in the real world will be severely degraded. In this paper, we propose a robust physical backdoor attack method, PTB (physical transformations for backdoors), to implement the backdoor attacks against deep learning models in the physical world. Specifically, in the training phase, we perform a series of physical transformations on these injected backdoor instances at each round of model training, so as to simulate various transformations that a backdoor may experience in real world, thus improves its physical robustness. Experimental results on the state-of-the-art face recognition model show that, compared with the methods that without PTB, the proposed attack method can significantly improve the performance of backdoor attacks in real physical world. Under various complex physical conditions, by injecting only a very small ratio (0.5 rate of physical backdoor attacks with the PTB method on VGGFace is 82 the attack success rate of backdoor attacks without the proposed PTB method is lower than 11 been affected. This paper is the first work on the robustness of physical backdoor attacks, and is hopeful for providing guideline for the subsequent physical backdoor works.



There are no comments yet.


page 1

page 4


Robust Attacks on Deep Learning Face Recognition in the Physical World

Deep neural networks (DNNs) have been increasingly used in face recognit...

Backdoor Attacks on Facial Recognition in the Physical World

Backdoor attacks embed hidden malicious behaviors inside deep neural net...

Few-shot Backdoor Defense Using Shapley Estimation

Deep neural networks have achieved impressive performance in a variety o...

3D Invisible Cloak

In this paper, we propose a novel physical stealth attack against the pe...

Can You Hear It? Backdoor Attacks via Ultrasonic Triggers

Deep neural networks represent a powerful option for many real-world app...

Acoustic Denial of Service Attacks on HDDs

Among storage components, hard disk drives (HDDs) have become the most c...

Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

One major goal of the AI security community is to securely and reliably ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.