Privacy-Preserving Data
Eiman discusses the evolution of privacy-preserving technologies, particularly the shift from traditional encryption methods to innovative approaches like homomorphic encryption. While encryption is seen as safe, the complexities of deep neural networks often lead to increased latency when using homomorphic encryption. The conversation highlights the importance of making data unintelligible to potential threats while still being usable for target models.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
SDS 843: Safe, Fast and Efficient AI — with Protopia’s Dr. Eiman Ebrahimi
Related Questions