Raw Event-Based Adversarial Attacks for Spiking Neural Networks with Configurable Latencies
Du, Xiao Shi, Wanli Zhao, Xiaohan Cao, Yang Gu, Bin Wu, Tieru
Du, Xiao
Shi, Wanli
Zhao, Xiaohan
Cao, Yang
Gu, Bin
Wu, Tieru
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Spiking Neural Networks (SNNs) and data from Dynamic Vision Sensors (DVSs) offer energy-efficient solutions for edge devices with limited battery life. The input latencies of event data to SNNs are critical for energy savings, and reducing these latencies through configurable parameters is essential. However, security concerns, particularly adversarial attacks on SNNs, are increasingly significant. While most existing research primarily focuses on attacking event sequences, which may not always be accessible, attacks on raw event streams with configurable latencies remain underexplored due to challenges such as extreme sparsity and the complexity of discrete optimization. This paper proposes a novel adversarial attack method on raw event streams with configurable latencies. To address sparsity and discrete optimization, we smooth the optimization by converting binary spikes into continuous values. Furthermore, we introduce an adaptively stochastic strategy for sampling attacking latencies. We apply regularization terms to maintain sparsity and ensure adversarial samples resemble raw event streams while approximating the target label. Extensive experiments on datasets such as N-MNIST, CIFAR10-DVS, N-Caltech-101, and Gesture-DVS demonstrate that our method consistently outperforms existing approaches, achieving higher attack success rates (ASR) across various latencies. Ablation studies validate the effectiveness of our contributions and highlight the impact of latency on the generation of adversarial samples.
Citation
X. Du, W. Shi, X. Zhao, Y. Cao, B. Gu, and T. Wu, “Raw Event-Based Adversarial Attacks for Spiking Neural Networks with Configurable Latencies,” Neural Networks, p. 108026, Aug. 2025, doi: 10.1016/J.NEUNET.2025.108026
Source
Neural Networks
Conference
Keywords
Machine Learning, Deep Learning, Spiking Neural Network, White-Box Adversarial Attack, Event-Based Tasks
Subjects
Source
Publisher
Elsevier