INTEL_REPORT
arXiv — Cryptography & Security (cs.CR) · published 5/14/2026, 4:00:00 AM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks arXiv:2605.13214v1 Announce Type: new 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 practical relevance, leaving open whether comparable undetectability extends to modern, end-to-end…
https://arxiv.org/abs/2605.13214
sha256:142c51ee23efb914872de3f0fef815cb37aba5bbad7d78cab2e8518d32cf99e7
What we pulled out
Deterministic extractor (IOC + allowlisted tokens + ATT&CK IDs present in DB).
Indicators
Linked with report → mentions → indicator. Values open the indicator workspace.
No indicators linked for this report.
Malware families
Allowlist token matches only.
Threat actors mentioned
Allowlist mentions — not a formal attribution verdict.
ATT&CK techniques
MITRE IDs referenced in text and present in local technique table.
CONTINUE INVESTIGATION
High-signal pivots without leaving the thread you started in search.
Browse the report corpus.