Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based Vision
Event-based dynamic vision sensors provide very sparse output in the form of spikes, which makes them suitable for low-power applications. Convolutional spiking neural networks model such event-based data and develop their full energy-saving potential when deployed on asynchronous neuromorphic hardware. Event-based vision being a nascent field, the sensitivity of spiking neural networks to potentially malicious adversarial attacks has received little attention so far. We show how white-box adversarial attack algorithms can be adapted to the discrete and sparse nature of event-based visual data, and demonstrate smaller perturbation magnitudes at higher success rates than the current state-of-the-art algorithms. For the first time, we also verify the effectiveness of these perturbations directly on neuromorphic hardware. Finally, we discuss the properties of the resulting perturbations, the effect of adversarial training as a defense strategy, and future directions.
Code (1)
Tasks
Adversarial AttackEvent-based visionSimilar Papers 제목 키워드 기반
R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors
Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS). This paper studies the robustness of SNNs again…
DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks
Spiking Neural Networks (SNNs), despite being energy-efficient when implemented on neuromorphic hardware and coupled with event-based Dynamic Vision Sensors (DVS), are vulnerable to security threats, such as adversarial …
Adversarial AttackToward Spiking Neural Network Local Learning Modules Resistant to Adversarial Attacks
Recent research has shown the vulnerability of Spiking Neural Networks (SNNs) under adversarial examples that are nearly indistinguishable from clean data in the context of frame-based and event-based information. The ma…
Adversarial AttackAdversarial RobustnessAttacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and for recent advances in their classification performance. However, unlike traditional deep learning approaches, the analysi…
Adversarial AttackInput-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain
As Spiking Neural Networks (SNNs) gain traction across various applications, understanding their security vulnerabilities becomes increasingly important. In this work, we focus on the adversarial attacks, which is perhap…
Adversarial AttackDecision Making