Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification

No. 2: AAAI-21 Technical Tracks 2

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 35

AAAI Technical Track on Computer Vision I

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a certain pattern called trigger, causing misclassification. Many existing trojan attacks have their triggers being input space patches/objects (e.g., a polygon with solid color) or simple input transformations such as Instagram filters. These simple triggers are susceptible to recent backdoor detection algorithms. We propose a novel deep feature space trojan attack with five characteristics: effectiveness, stealthiness, controllability, robustness and reliance on deep features. We conduct extensive experiments on 9 image classifiers on various datasets including ImageNet to demonstrate these properties and show that our attack can evade state-of-the-art defense.

10.1609/aaai.v35i2.16201