PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks

Documenti analoghi

• Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks
  di: Njungle, Nges Brian, et al.
  Pubblicazione: (2026)
• FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
  di: Njungle, Nges Brian, et al.
  Pubblicazione: (2025)
• Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection
  di: Njungle, Nges Brian, et al.
  Pubblicazione: (2025)
• Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
  di: Njungle, Nges Brian, et al.
  Pubblicazione: (2025)
• Spatially Disaggregated Energy Consumption and Emissions in End-use Sectors for Germany and Spain
  di: Patil, Shruthi, et al.
  Pubblicazione: (2025)