INTEL_REPORT
arXiv — Cryptography & Security (cs.CR) · published 6/2/2026, 4:00:00 AM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs arXiv:2606.00813v1 Announce Type: new Abstract: Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with quality-diversity evolution (MAP-Elites) as an automated red-teaming probe, we find that Gemma 3 (12B) exhibits 68.7% +/- 5.7% attack success rate (ASR; mean +/- std, 3 seeds), significa…
https://arxiv.org/abs/2606.00813
sha256:3f738ec1995885dd38295ef3124368fc8f2bd2b6531660e1d963f46e48806d28
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.
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.
Neighborhood from the first linked indicator.