INTEL_REPORT
arXiv — Cryptography & Security (cs.CR) · published 7/9/2026, 4:00:00 AM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages arXiv:2607.06596v1 Announce Type: new Abstract: Trusted monitoring is a central defense in AI control: a cheaper trusted model scores an untrusted model's actions for sabotage, and the most suspicious are audited or deferred. Such monitors are evaluated against one or two untrusted models, and the accuracy is reported as a property of the monitor. We ask whether it is partly a property o…
https://arxiv.org/abs/2607.06596
sha256:59e65b32d89fcb7616f2f9f0569e7605ae4bc9b2c51b86c9fbff58ae18e325d9
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.