DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers

TL;DR

DeepBaR introduces a fault-based backdoor attack method on neural networks that achieves high success rates with minimal impact on normal accuracy, posing significant security risks.

Contribution

This work presents a novel fault injection technique for implanting backdoors in neural networks during training, especially fine-tuning, which was not previously explored.

Findings

Attack success rate up to 98.30%

Minimal accuracy degradation on non-malicious inputs

Ability to generate inputs resembling one class but classified as another

Abstract

Machine Learning using neural networks has received prominent attention recently because of its success in solving a wide variety of computational tasks, in particular in the field of computer vision. However, several works have drawn attention to potential security risks involved with the training and implementation of such networks. In this work, we introduce DeepBaR, a novel approach that implants backdoors on neural networks by faulting their behavior at training, especially during fine-tuning. Our technique aims to generate adversarial samples by optimizing a custom loss function that mimics the implanted backdoors while adding an almost non-visible trigger in the image. We attack three popular convolutional neural network architectures and show that DeepBaR attacks have a success rate of up to 98.30\%. Furthermore, DeepBaR does not significantly affect the accuracy of the attacked networks after deployment when non-malicious inputs are given. Remarkably, DeepBaR allows attackers to choose an input that looks similar to a given class, from a human perspective, but that will be classified as belonging to an arbitrary target class.