English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep neural networks (DNNs) have demonstrated remarkable performance acrossvarious tasks, including image and speech recognition. However, maximizing theeffectiveness of DNNs requires meticulous optimization of numeroushyperparameters and network parameters through training. Moreover,high-performance DNNs entail many parameters, which consume significant energyduring training. In order to overcome these challenges, researchers have turnedto spiking neural networks (SNNs), which offer enhanced energy efficiency andbiologically plausible data processing capabilities, rendering them highlysuitable for sensory data tasks, particularly in neuromorphic data. Despitetheir advantages, SNNs, like DNNs, are susceptible to various threats,including adversarial examples and backdoor attacks. Yet, the field of SNNsstill needs to be explored in terms of understanding and countering theseattacks.  This paper delves into backdoor attacks in SNNs using neuromorphic datasetsand diverse triggers. Specifically, we explore backdoor triggers withinneuromorphic data that can manipulate their position and color, providing abroader scope of possibilities than conventional triggers in domains likeimages. We present various attack strategies, achieving an attack success rateof up to 100\% while maintaining a negligible impact on clean accuracy.Furthermore, we assess these attacks' stealthiness, revealing that our mostpotent attacks possess significant stealth capabilities. Lastly, we adaptseveral state-of-the-art defenses from the image domain, evaluating theirefficacy on neuromorphic data and uncovering instances where they fall short,leading to compromised performance.

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