L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set

Abstract

Backdoor attacks (BAs) are an emerging form of adversarial attack typically against deep neural network image classifiers. The attacker aims to have the classifier learn to classify to a target class when test images from one or more source classes contain a backdoor pattern, while maintaining high accuracy on all clean test images. Reverse-Engineering-based Defenses (REDs) against BAs do not require access to the training set but only to an independent clean dataset. Unfortunately, most existing REDs rely on an unrealistic assumption that all classes except the target class are source classes of the attack. REDs that do not rely on this assumption often require a large set of clean images and heavy computation. In this paper, we propose a Lagrangian-based RED (L-RED) that does not require knowledge of the number of source classes (or whether an attack is present). Our defense requires very few clean images to effectively detect BAs and is computationally efficient. Notably, we detect 56 out of 60 BAs using only two clean images per class in our experiments on CIFAR-10.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Spectral Signatures in Backdoor Attacks
• Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
• TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
• Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks