Indicator
Type url · source intel_report_ingest
Related reports (2)
Title/body text match only.
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety arXiv:2606.00801v1 Announce Type: new Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode coll
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
Sources / connectors (1)
Deduped connector weight from graph context.
CONTINUE INVESTIGATION
High-signal pivots without leaving the thread you started in search.
Structured pivots from local graph context.
See edges, pivots, and corroboration at a glance.
Full inspector with neighbor expansion.