TELOS Adversarial Validation Dataset

Validation results for TELOS AI governance framework demonstrating 0 observed attack successes across 2,550 adversarial attacks from four evaluation sources (AILuminate, MedSafetyBench, HarmBench, SB 243-aligned suite). Includes full forensic audit trail with JSONL governance event logs. Key Results: - 2,550 attacks validated (1,200 AILuminate + 900 MedSafetyBench + 400 HarmBench + 50 SB 243- aligned) - 0/2,550 observed attack successes - 95% CI upper bound: ~0.15% - 95.8% autonomous blocking (Tier 1) - Six Sigma performance: <2% human escalation - Three-tier governance architecture (Primacy Attractor → RAG → Human) Benchmarks: - AILuminate Standard Benchmark (1,200 prompts, 12 NIST AI RMF harm categories) - MedSafetyBench (900 prompts, NeurIPS 2024) - HarmBench (400 prompts, Center for AI Safety) - SB 243-Aligned Evaluation Suite (50 prompts, internal benchmark aligned with California child safety categories) Files Included: - Complete validation datasets from all four evaluation sources - Statistical analysis summary - Tier distribution data - ERRATA_v1.1.md (validation status clarification) Forensic Audit Trail (v2.0) - harmbench_forensic_forensic_summary.json - HarmBench aggregate statistics - harmbench_forensic_forensic_results.json - HarmBench per-prompt forensic data - harmbench_forensic_fidelity_distribution .csv - HarmBench fidelity scores - harmbench_forensic_governance_report.html - HarmBench interactive visualization - traces/session_harmbench_forensic_*.jsonl - HarmBench JSONL governance event log - medsafetybench_forensic_forensic_summary.json - MedSafetyBench aggregate statistics - medsafetybench_forensic_forensic_results.json - MedSafetyBench per-prompt forensic data - medsafetybench_forensic_fidelity_distribution.csv - MedSafetyBench fidelity scores - medsafetybench_forensic_governance_report.html - MedSafetyBench interactive visualization - traces/session_medsafetybench_forensic_*.jsonl - MedSafetyBench JSONL governance event log Validation Status: This dataset demonstrates proof-of-concept validation of the TELOS governance methodology under ' black-box threat models. The healthcare PA and RAG corpus were constructed from authoritative public domain sources (HIPAA Privacy Rule, HHS guidance, peer-reviewed clinical literature) but have not been formally validated by external healthcare compliance professionals or clinical researchers. Results should be interpreted as methodology demonstration, not certification for clinical deployment. See ERRATA_v1.1.md for details. License: CC BY 4.0 Validation Date: Original validation 2024-12-21 (forensic audit added 2026-01-25, AILuminate/SB 243- aligned validation added 2026-01) Changes in this version (2026-07-27): removes third-party benchmark prompt text that earlier versions redistributed, replacing each removed field with a SHA-256 digest of the removed text. Rendered HTML governance reports embedding prompt text are removed pending regeneration from clean data. A runtime configuration string is withheld. No TELOS-authored scores, verdicts, hashes, distributions, or analyses were altered. Third-party benchmark attribution. This version contains TELOS-authored evaluation outputs (scores, verdicts, tier distributions, and SHA-256 digests) produced against two third-party benchmarks whose prompt text is NOT redistributed here: HarmBench (Mazeika et al., 2024; MIT License) and MedSafetyBench (Han et al., 2024; MIT License with a research-use-only condition stated by its authors). Each removed prompt is represented by a SHA-256 digest so results remain joinable to the upstream datasets by researchers who obtain them from their original sources under their original terms. The license of this record applies to TELOS-authored content only. File list note: the two interactive governance report HTML files referenced above are not included in this version, because the rendered reports embedded benchmark prompt text. They will be regenerated from clean data.