Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Main Conference Track
Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu
Convolutional neural networks (CNN) can be manipulated to perform specific behaviors when encountering a particular trigger pattern without affecting the performance on normal samples, which is referred to as backdoor attack. The backdoor attack is usually achieved by injecting a small proportion of poisoned samples into the training set, through which the victim trains a model embedded with the designated backdoor. In this work, we demonstrate that backdoor neurons are exposed by their pre-activation distributions, where populations from benign data and poisoned data show significantly different moments. This property is shown to be attack-invariant and allows us to efficiently locate backdoor neurons. On this basis, we make several proper assumptions on the neuron activation distributions, and propose two backdoor neuron detection strategies based on (1) the differential entropy of the neurons, and (2) the Kullback-Leibler divergence between the benign sample distribution and a poisoned statistics based hypothetical distribution. Experimental results show that our proposed defense strategies are both efficient and effective against various backdoor attacks.