AI RESEARCH
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
arXiv CS.LG
•
ArXi:2605.13214v1 Announce Type: cross 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 practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end trained networks.