Accuracy-Robustness Trade Off via Spiking Neural Network Gradient Sparsity Trail
This addresses adversarial robustness in energy-efficient SNNs for vision applications, but it is incremental as it builds on prior work on sparse gradients.
The paper tackles the challenge of adversarial robustness in Spiking Neural Networks (SNNs) for vision tasks, finding that SNNs can achieve state-of-the-art defense performance through natural gradient sparsity without explicit regularization, but this leads to a trade-off where sparsity improves robustness while impairing generalization.
Spiking Neural Networks (SNNs) have attracted growing interest in both computational neuroscience and artificial intelligence, primarily due to their inherent energy efficiency and compact memory footprint. However, achieving adversarial robustness in SNNs, particularly for vision-related tasks, remains a nascent and underexplored challenge. Recent studies have proposed leveraging sparse gradients as a form of regularization to enhance robustness against adversarial perturbations. In this work, we present a surprising finding: under specific architectural configurations, SNNs exhibit natural gradient sparsity and can achieve state-of-the-art adversarial defense performance without the need for any explicit regularization. Further analysis reveals a trade-off between robustness and generalization: while sparse gradients contribute to improved adversarial resilience, they can impair the model's ability to generalize; conversely, denser gradients support better generalization but increase vulnerability to attacks.