Edge learning is a new and powerful approach to training models across distributed clients while protecting the privacy of their data.
This approach is expected to be embedded within future network infrastructures, including 6G, to solve challenging problems such as resource management and behaviour prediction. However, edge learning in general, and distributed deep learning, in particular, have been discovered to be susceptible to tampering and manipulation. This survey article provides a holistic review of the most recent research focused on edge learning vulnerabilities and defenses for 6G-enabled IoT.