Towards Invisible Backdoor Attacks in the Frequency Domain against Deep Neural Networks

TL;DR

This paper introduces a novel frequency-domain backdoor attack on deep neural networks that embeds triggers in the Fourier spectrum of images, making them undetectable to humans while maintaining high attack success rates.

Contribution

It proposes a new stealthy backdoor attack method using Fourier transforms to hide triggers in the frequency domain of images, enhancing concealment against human detection.

Findings

Successfully fools both humans and DNNs with subtle perturbations.

Achieves high attack success rate without degrading model accuracy.

Effective across multiple benchmark datasets.

Abstract

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By injecting malicious data into the training set, an adversary can plant the backdoor into the original model. The backdoor can remain hidden indefinitely until activated by a sample with a specific trigger, which is hugely concealed, bringing serious security risks to critical applications. However, one main limitation of current backdoor attacks is that the trigger is often visible to human perception. Therefore, it is crucial to study the stealthiness of backdoor triggers. In this paper, we propose a novel frequency-domain backdooring technique. In particular, our method aims to add a backdoor trigger in the frequency domain of original images via Discrete Fourier Transform, thus hidding the trigger. We evaluate our method on three benchmark datasets: MNIST, CIFAR-10 and Imagenette. Our experiments show that we can simultaneously fool human inspection and DNN models. We further apply two image similarity evaluation metrics to illustrate that our method adds the most subtle perturbation without compromising attack success rate and clean sample accuracy.