arxiv
PublishedSeptember 10, 2026 at 4:00 AM
Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks
Publisher summary· verbatim
arXiv:2605.13214v3 Announce Type: replace-cross Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited practic
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivPlanning and Scheduling Business Processes under Control-Flow Uncertainty13harxivSIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detection13harxivWAPP: Safe Learning of Positive Security WAF Policies from Live Traffic13harxivPAN: A World Model for General, Actionable, and Long-Horizon World Simulation13hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗