Phantom Forgetting: How BatchNorm State Fakes Deletion in Edge Split Machine Unlearning
Split-learning unlearning on edge devices may leave residual data traces in BatchNorm state—a gap with direct implications for GDPR erasure compliance in federated AI deployments.
Summary written by editorial AI · Source link below
arXiv:2610.34800v1 Announce Type: new Abstract: Split learning is a natural fit for edge intelligence: a resource-constrained edge device runs the first layers of a network and offloads the remainder to a server, so that raw data never leave the device. When such a system must unlearn revoked or sensitive data for example to honor a right-to-erasure request, the deletion is commonly assessed through changes in forget-set accuracy. However, inference on an edge-server split also depends on non-l
Editorial Analysis
Enterprises relying on edge-based split learning for privacy must verify that unlearning actually erases data, not just appears to.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the Research Desk
- Firecracker VM Escape: PwnEscape Part 23d
- A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow3d
- LABBA: LLM-Assisted Behavioral Biometric Authentication3d
- A Cyber Range Evaluation of Inductive Autonomous Network Incident Response Agents3d
- KeHoSu: Keyed Homoglyph Substitution for Authenticated Text Provenance over Copy-Paste Channels3d