Threshold Switching Memristor-Based Radial-Based Spiking Neuron Circuit for Conversion-Based Spiking Neural Networks Adversarial Attack Improvement

作者：Zuheng Wu, Wei Li, Jianxun Zou, Zhe Feng, Tao Chen, Xiuquan Fang, Xing Li, Yunlai Zhu, Zuyu Xu, Yuehua Dai · 发表于：IEEE Transactions on Circuits & Systems II Express Briefs · 年份：2023 · DOI：10.1109/tcsii.2023.3318592 · 被引用次数：8 · 研究领域：Advanced Memory and Neural Computing、Ferroelectric and Negative Capacitance Devices、Neuroscience and Neural Engineering

The analog neural network to spiking neural network (ANN-to-SNN) conversion is an effective method for improving the performance of SNNs. However, the existing mainstream conversion method (rectified linear unit, ReLU) still face the problem of weak ability for adversarial attacks. In this brief, inspired by the radial basis function and the “near enhancement and far inhibition (NEFI)” properties of biological neurons, a threshold switching (TS) memristor based radial basis spiking neuron (RBSN) circuit is proposed for the ANN-to-SNN conversion implementation. The results indicate that the RBSN circuit can effectively implement the NEFI spiking properties, which is benefit for filtering the adversarial attacks information. Furthermore, the comparison of ReLU and RBSN conversion methods based ANN-to-SNN for MNIST dataset classification task was performed. The results indicate that the RBSN shows obviously advantage than the ReLU for confronting the adversarial attacks. The accuracy of RBSN based ANN-to-SNN achieved ~80.6%, even the input data containing 40% attack information, whereas the ReLU based ANN-to SNN only achieved ~49.2%. This brief provides new ideas for the security design of neuromorphic computing systems.