Aondor Research

Published Work

Published work behind the Aondor governance pipeline. PatternWall pre-inference detection, Sensus post-inference evaluation, and dual-pipeline benchmark results across three frontier AI models.

Joint Paper · March 2026

Defense in Depth: AI Governance Through Dual-Pipeline Architecture

Melissa K. Pinkston · LKM Constructs · Patent Pending

Combines PatternWall v5.0 pre-inference interception with Sensus v4.0 post-inference evaluation into a bidirectional feedback loop. Tested across Claude Opus 4.6, GPT-5.2, and Grok 4.1 on 35 adversarial red team turns and 120 CyberGym exploit tasks. Zero overlap between layers (BOTH_CAUGHT = 0) confirms complementary coverage across non-overlapping threat surfaces.

76.7–98.3%Combined Detection
3Frontier Models
0BOTH_CAUGHT Overlap
+14.3ppFeedback Loop Gain

v5 PatternWall + v4 Sensus

Model Raw (No Governance) Combined Pipeline True Misses
Claude Opus 4.6 5.7% / 3.3% 91.4%† / 98.3% 3 RT / 2 CG
GPT-5.2 25.7% / 81.7% 82.9% / 98.3%* 6 RT / 2 CG
Grok 4.1 0.0% / 3.3% 85.7%† / 93.9%* 5 RT / 6 CG

*Adjusted for empty responses per Section 4.2.1 of joint paper. †With bidirectional feedback loop active (+14.3pp Opus, +2.8pp Grok). RT = Red Team (35 adversarial turns), CG = CyberGym (120 exploit tasks).

Preprint · February 2026

PatternWall: Constitutional Governance Middleware for AI Safety

Melissa Pinkston · LKM Constructs

A pre-filter architecture for model-agnostic adversarial detection. PatternWall intercepts prompts before they reach an AI model, enforcing governance as deterministic infrastructure rather than relying on model-level training or provider-specific tuning.

100%Attack Detection
96.4%Hard Block
5Models Tested
0%False Positives
White Paper · February 2026

Sensus: Model-Agnostic AI Governance Through Multi-Dimensional Content Evaluation

Melissa K. Pinkston · LKM Constructs · Patent Pending

A post-inference governance engine that evaluates AI outputs across five weighted dimensions to detect harmful content bypassing model-native safety. Benchmarked across five frontier models on 1,507 CVE exploit tasks and 28 multi-turn adversarial campaigns. Demonstrates that infrastructure-level governance is necessary because model-level safety is unreliable, inconsistent, and provider-dependent.

85.7–96.4%Effective Governance
5Frontier Models
1,507CVE Tasks Tested
0Regressions
Published benchmarks demonstrate results without revealing proprietary implementation details.
← Back to Aondor Overview