most citedSafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)

8 citations · 10 across the 2 of their papers we have counts for

collaborators
Showing cs.CRShow all

2 papers · 1 filter

cs.CR2025★ 8 cited

SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)

Phillip Rieger, Alessandro Pegoraro, Kavita Kumari +3

Split Learning (SL) is a distributed deep learning approach enabling multiple clients and a server to collaboratively train and infer on a shared deep neural network (DNN) without…

cs.CR2024★ 2 cited

Phantom: Untargeted Poisoning Attacks on Semi-Supervised Learning (Full Version)

Jonathan Knauer, Phillip Rieger, Hossein Fereidooni +1

Deep Neural Networks (DNNs) can handle increasingly complex tasks, albeit they require rapidly expanding training datasets. Collecting data from platforms with user-generated conte…