arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20548cs.CV
收藏

对抗攻击下的鲁棒脉冲神经网络

Robust Spiking Neural Networks Against Adversarial Attacks

University of Electronic Science and Technology of China(电子科技大学);Northumbria University(诺丁汉大学);Shenzhen Loop Area Institute(深圳河套学院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Shuai Wang, Malu Zhang, Yulin Jiang, Dehao Zhang, Ammar Belatreche, Yu Liang, Yimeng Shan, Zijian Zhou, Yang Yang, Haizhou Li

AI总结:

本文提出阈值保护优化方法,通过增加梯度稀疏性和引入噪声脉冲神经元,提升直接训练SNNs在对抗攻击下的鲁棒性。

摘要:

脉冲神经网络(SNNs)由于其生物合理性和脉冲驱动特性,成为一种有前途的能效神经形态计算范式。然而,SNNs在复杂对抗环境中的鲁棒性仍然受到显著限制。在本研究中,我们理论证明了那些阈值邻近的脉冲神经元是限制直接训练SNNs鲁棒性的关键因素。我们发现这些神经元设定了对抗攻击最大潜在强度的上限,并且容易在微小扰动下发生状态翻转。为了解决这一挑战,我们提出了一种阈值保护优化(TGO)方法,其包含两个关键方面。首先,我们将额外的约束纳入损失函数中,以将神经元膜电位移离其阈值。这增加了SNNs的梯度稀疏性,从而降低对抗攻击的理论上限。其次,我们引入了噪声脉冲神经元,将神经元放电机制从确定性转换为概率性,从而降低由于微小扰动导致的状态翻转概率。在标准对抗场景中进行的广泛实验证明,我们的方法显著增强了直接训练SNNs的鲁棒性。这些发现为推进更可靠和安全的神经形态计算在实际应用中的发展铺平了道路。

英文摘要:

Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments remains significantly constrained. In this study, we theoretically demonstrate that those threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs. We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances. To address this challenge, we propose a Threshold Guarding Optimization (TGO) method, which comprises two key aspects. First, we incorporate additional constraints into the loss function to move neurons' membrane potentials away from their thresholds. It increases SNNs' gradient sparsity, thereby reducing the theoretical upper bound of adversarial attacks. Second, we introduce noisy spiking neurons to transition the neuronal firing mechanism from deterministic to probabilistic, decreasing their state-flipping probability due to minor disturbances. Extensive experiments conducted in standard adversarial scenarios prove that our method significantly enhances the robustness of directly trained SNNs. These findings pave the way for advancing more reliable and secure neuromorphic computing in real-world applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑