Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data

by   Gorka Abad, et al.

Deep neural networks (DNNs) have achieved excellent results in various tasks, including image and speech recognition. However, optimizing the performance of DNNs requires careful tuning of multiple hyperparameters and network parameters via training. High-performance DNNs utilize a large number of parameters, corresponding to high energy consumption during training. To address these limitations, researchers have developed spiking neural networks (SNNs), which are more energy-efficient and can process data in a biologically plausible manner, making them well-suited for tasks involving sensory data processing, i.e., neuromorphic data. Like DNNs, SNNs are vulnerable to various threats, such as adversarial examples and backdoor attacks. Yet, the attacks and countermeasures for SNNs have been almost fully unexplored. This paper investigates the application of backdoor attacks in SNNs using neuromorphic datasets and different triggers. More precisely, backdoor triggers in neuromorphic data can change their position and color, allowing a larger range of possibilities than common triggers in, e.g., the image domain. We propose different attacks achieving up to 100% attack success rate without noticeable clean accuracy degradation. We also evaluate the stealthiness of the attacks via the structural similarity metric, showing our most powerful attacks being also stealthy. Finally, we adapt the state-of-the-art defenses from the image domain, demonstrating they are not necessarily effective for neuromorphic data resulting in inaccurate performance.


page 3

page 5


Security-Aware Approximate Spiking Neural Networks

Deep Neural Networks (DNNs) and Spiking Neural Networks (SNNs) are both ...

Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks

Spiking neural networks (SNNs) have great potential for energy-efficient...

SNN under Attack: are Spiking Deep Belief Networks vulnerable to Adversarial Examples?

Recently, many adversarial examples have emerged for Deep Neural Network...

NU-AIR – A Neuromorphic Urban Aerial Dataset for Detection and Localization of Pedestrians and Vehicles

Annotated imagery capturing pedestrians and vehicles in an urban environ...

An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor

Spiking Neural Networks (SNNs), the third generation NNs, have come unde...

Evolving Connectivity for Recurrent Spiking Neural Networks

Recurrent spiking neural networks (RSNNs) hold great potential for advan...

The Yin-Yang dataset

The Yin-Yang dataset was developed for research on biologically plausibl...

Please sign up or login with your details

Forgot password? Click here to reset