| --- |
| license: other |
| license_name: qtrust-research |
| base_model: huggingface/codeberta-language-id |
| tags: |
| - cryptography |
| - post-quantum-cryptography |
| - code-classification |
| - crypto-discovery |
| metrics: |
| - f1 |
| - precision |
| - recall |
| --- |
| |
| # Q-Trust CryptoCodeDetector (CodeBERTa fine-tune) |
|
|
| Fine-tuned crypto-usage discovery model from [Q-Trust](https://github.com/humoge7502/q-trust) |
| (`qtrust_ai/` intelligence layer). Detects cryptographic API usage and algorithm families in |
| source code — the discovery stage that feeds CBOM generation and PQC migration planning. |
|
|
| ## Training |
|
|
| - **Corpus:** 13,973 real code files — SolidiFI, SmartBugs, EIPs, WebAuthn blockchain contracts, OSS crypto repos |
| - **Schedule:** 4-epoch GPU fine-tune (A100), deterministic seed (same seed → same F1) |
| - **Dataset:** [`KRPur/q-trust-datasets`](https://huggingface.co/datasets/KRPur/q-trust-datasets) (`code_corpus.json`) |
|
|
| ## Held-out results (repo-disjoint, n=2415) |
|
|
| | Metric | Q-Trust ensemble | Rules-only | Majority | Random | |
| |---|---|---|---|---| |
| | **F1** | **0.9525** | 0.673 | 0.8683 | 0.5981 | |
| | Precision | 0.952 | 0.979 | — | — | |
| | Recall | 0.953 | 0.513 | 1.0 | — | |
|
|
| Source: `qtrust_ai/artifacts/benchmark_comparison.json` (seed 42) in the GitHub repo. |
|
|
| ## Usage |
|
|
| ```python |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer |
| m = AutoModelForSequenceClassification.from_pretrained("KRPur/q-trust-codebert") |
| t = AutoTokenizer.from_pretrained("KRPur/q-trust-codebert") |
| ``` |
|
|
