KerbNet : A QoE-Aware Kernel-Based Backdoor Attack Framework

Xueluan Gong

doi:10.1109/TDSC.2023.3286842

KerbNet : A QoE-Aware Kernel-Based Backdoor Attack Framework

2024-07-01

2

PRE

AI

DOI：10.1109/TDSC.2023.3286842

Original

Original request for help

Save

Abstract

En 中文

Deep neural networks are vulnerable to backdoor attacks, where a specially-designed trigger will lead to misclassification of any benign samples. However, existing backdoor attacks usually impose conspicuous patch triggers on images, which are easily detected by humans and defense algorithms. Existing works on invisible triggers, however, either have reduced attack success rate or yield detectable patterns to visual inspections. In this article, we propose KerbNet, a kernel-based backdoor attack framework, which applies kernel operations to clean samples as the trigger to incur misclassification. The kernel-processed samples achieve a high attack success rate while appearing natural with high Quality-of-Experience (QoE). We carefully design the kernel trigger generation algorithm by exploiting the neural network structure to propagate the influence of the trigger to the target misclassification label under the QoE constraint. We conduct extensive experiments on five datasets, i.e., MNIST, GTSRB, CIFAR-10, CelebA, and ImageNette to evaluate the effectiveness and practicality of KerbNet under the impact of various factors, including neuron-residing layer, kernel size, base image, loss function, model structure, and so on. We also show that our proposed attacks can evade state-of-the-art defense strategies and visual inspections. Code will be available after publication.

Keywords:

Kernel

Inspection

Visualization

Quality of experience

Training

Biological neural networks

Smoothing methods

Deep neural network

backdoor attack

quality-of-experience

kernel algorithm

KerbNet : A QoE-Aware Kernel-Based Backdoor Attack Framework

Abstract

Journal

Organization