New MDSE attack fools Spiking Neural Networks and traditional models

Researchers have developed a new adversarial attack method called Mixed Dynamic Spiking Estimation (MDSE) specifically for Spiking Neural Networks (SNNs). This attack demonstrates that the effectiveness of white-box adversarial attacks on SNNs is heavily influenced by the choice of surrogate gradient estimator. The MDSE attack is designed to exploit multiple surrogate gradient estimators simultaneously, enabling it to generate adversarial examples that can fool both SNNs and traditional non-SNN models like Vision Transformers and CNNs. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a novel attack that can fool both SNNs and traditional neural networks, highlighting security vulnerabilities in energy-efficient AI models.

RANK_REASON Academic paper detailing a new adversarial attack method for SNNs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• CIFAR-10
• CIFAR-100
• CNNs
• ImageNet
• Mixed Dynamic Spiking Estimation (MDSE)
• Nuo Xu
• Spiking Neural Networks (SNNs)
• Vision Transformers (ViTs)

• paper
• safety