Deep Neural Networks (DNNs) and Spiking Neural Networks (SNNs) are both known for their susceptibility to adversarial attacks. Therefore, researchers in the recent past have extensively studied the robustness and defense of DNNs and SNNs under adversarial attacks. Compared to accurate SNNs (AccSNN), approximate SNNs (AxSNNs) are known to be up to 4X more energy-efficient for ultra-low power applications. Unfortunately, the robustness of AxSNNs under adversarial attacks is yet unexplored. In this paper, we first extensively analyze the robustness of AxSNNs with different structural parameters and approximation levels under two gradient-based and two neuromorphic attacks. Then, we propose two novel defense methods, i.e., precision scaling and approximate quantization-aware filtering (AQF), for securing AxSNNs. We evaluated the effectiveness of these two defense methods using both static and neuromorphic datasets. Our results demonstrate that AxSNNs are more prone to adversarial attacks than AccSNNs, but precision scaling and AQF significantly improve the robustness of AxSNNs. For instance, a PGD attack on AxSNN results in a 72\% accuracy loss compared to AccSNN without any attack, whereas the same attack on the precision-scaled AxSNN leads to only a 17\% accuracy loss in the static MNIST dataset (4X robustness improvement). Similarly, a Sparse Attack on AxSNN leads to a 77\% accuracy loss when compared to AccSNN without any attack, whereas the same attack on an AxSNN with AQF leads to only a 2\% accuracy loss in the neuromorphic DVS128 Gesture dataset (38X robustness improvement).
Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
Lehigh University(莱文大学);University of Minnesota Twin Cities(明尼苏达大学双城分校);North Carolina State University(北卡罗来纳州立大学);University of Rhode Island(罗德岛大学);Northeastern University(东北大学)
Toward Robust Spiking Neural Network Against Adversarial Perturbation
University of California, Santa Barbara(加州大学圣巴巴拉分校);Drexel University(德雷塞尔大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所);Tsinghua University(清华大学)
College of Computer Science and Technology(计算机科学与技术学院);State Key Laboratory of Brain-machine Intelligence(脑机智能国家重点实验室);Zhejiang University(浙江大学);School of Software Technology(软件学院);School of Computer Science(计算机学院);Fudan University(复旦大学);Institute of Data Science(数据科学研究院);National University of Singapore(新加坡国立大学);First Affiliated Hospital(第一附属医院);Zhejiang University School of Medicine(浙江大学医学院);Distributed Systems Group(分布式系统组);Technische Universität Wien(维也纳技术大学);ICREA Barcelona(巴塞罗那ICREA);The University of Sydney(悉尼大学)
ILIF: Temporal Inhibitory Leaky Integrate-and-Fire Neuron for Overactivation in Spiking Neural Networks
Department of Data Science and AI, Monash University(墨尔本大学数据科学与人工智能系);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);School of Software, Northeastern University(东北大学软件学院)
Differentiable architecture search with multi-dimensional attention for spiking neural networks
Nanjing Institute of Intelligent Technology(南京智能技术研究院);School of Integrated Circuits, University of Chinese Academy of Sciences(中国科学院大学集成电路学院);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Institute of Microelectronics, Chinese Academy of Sciences(中国科学院微电子研究所)
Evolving Efficient Genetic Encoding for Deep Spiking Neural Networks
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Center for Long-term Artificial Intelligence(长期人工智能中心);Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Chinese Academy of Sciences(中国科学院脑认知与脑智能技术重点实验室)
Emerging Threats and Countermeasures in Neuromorphic Systems: A Survey
Faculty of Science and Engineering, University of Groningen(科学与工程学院,格罗宁根大学);Faculty of Electrical Engineering and Computing, University of Zagreb(电气工程与计算学院,扎格reb大学);Radboud University(拉德堡德大学);Centre for Secure Information Technologies (CSIT), Queen's University Belfast(安全信息科技中心(CSIT),女王大学贝尔法斯特分校);Faculty of Computer Science and Mathematics, University of Passau(计算机科学与数学学院,帕绍大学);University of Amsterdam(阿姆斯特丹大学);Digital Security (DiS) Group, Radboud University(数字安全(DiS)小组,拉德堡德大学)
Privacy-Preserving Product-Quantized Approximate Nearest Neighbor Search Framework for Large-scale Datasets via A Hybrid of Fully Homomorphic Encryption and Trusted Execution Environment