[USENIX Security 2026] Attesting Model Lineage by Consisted Knowledge Evolution with Fine-Tuning Trajectory
-
Updated
Sep 14, 2026 - Python
#
model-lineage
Here are 6 public repositories matching this topic...
LLM distillation detection & model fingerprinting via statistical forensics — behavioral probing, stylistic signatures & representation similarity. CLI + MCP ready.
python cli mcp ai-security llm ai-data-pipeline model-fingerprint distillation-detection model-lineage knowlyr
-
Updated
Mar 15, 2026 - Python
A protocol for collecting, fusing, and assessing multi-source evidence of model derivation without treating audit signals as automatic legal or royalty verdicts.
ai-audit model-lineage model-provenance evidence-fusion derivation-audit audit-reconciliation multi-auditor decision-handoff
-
Updated
Sep 9, 2026 - Python
AI system governance logger with prompt response and model lineage tracking
-
Updated
Feb 23, 2026 - Python
Git blame for ML models. Track how your models evolve over time — lineage, data snapshots, performance deltas, and regression debugging for continual learning workflows.
-
Updated
Mar 8, 2026 - Python
Black-box LLM lineage experiments using lossless compression
-
Updated
Aug 9, 2026 - Python
Add this topic to your repo
To associate your repository with the model-lineage topic, visit your repo's landing page and select "manage topics."