Secure By Dezign
Federated Learning Security: When Collaboration Becomes Risk
March 4 · 17 min · Season 1 · Episode 5 · 9.0 MB
0:00-17:57
Streams straight from the publisher. podnod never proxies or re-hosts episode audio.
The distributed ML paradigm that promised privacy may be your biggest attack surface yet. Deep-dive into poisoning attacks against federated models, gradient inversion, and Byzantine fault tolerance.
No links were found in this episode’s notes.