Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters

Abstract

Deep Learning (DL) algorithms have gained popularity owing to their practical problem-solving capacity. However, they suffer from a serious integrity threat, i.e., their vulnerability to adversarial attacks. In the quest for DL trustworthiness, recent works claimed the inherent robustness of Spiking Neural Networks (SNNs) to these attacks, without considering the variability in their structural spiking parameters. This paper explores the security enhancement of SNNs through internal structural parameters. Specifically, we investigate the SNNs robustness to adversarial attacks with different values of the neuron's firing voltage thresholds and time window boundaries. We thoroughly study SNNs security under different adversarial attacks in the strong white-box setting, with different noise budgets and under variable spiking parameters. Our results show a significant impact of the structural parameters on the SNNs' security, and promising sweet spots can be reached to design trustworthy SNNs with 85% higher robustness than a traditional non-spiking DL system. To the best of our knowledge, this is the first work that investigates the impact of structural parameters on SNNs robustness to adversarial attacks. The proposed contributions and the experimental framework is available online to the community for reproducible research.

Accepted for publication at the 24th Design, Automation and Test in Europe (DATE'21), February, 2021

References in corpus (12)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Intriguing properties of neural networks
• Adversarial Examples: Attacks and Defenses for Deep Learning
• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• Deep Learning in the Automotive Industry: Applications and Tools
• Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead
• DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks
• CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks
• Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
• Closing the Accuracy Gap in an Event-Based Visual Recognition Task

Cited by in corpus (5)

• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack
• A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
• HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise
• Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems