Commercial 6,000-Row Multi-Domain Security Suite v4 (Zero Overlap with v1–v3): Need an unseen, contamination-free benchmark to evaluate or fine-tune beyond public splits? Explore the 6,000-row Oxford Digital Enterprise Security Remediation Suite v4 (
1,200Solidity EVM +1,200Rust/Solana Anchor +1,200Python/TS AI Agent & MCP +1,200Go/TS/Python Cloud APIs +1,200K8s/Terraform IaC in Parquet/CSV/JSONL):
- Live Interactive Explorer Space:
Offlin33er/oxford-digital-security-suite-v4· 100-Row Sample:Offlin33er/solidity-exploit-reasoning-v4-sample- Instant Stripe Checkout: $99 Single-Seat Indie → · $599 Team Pro → · $1,499 Enterprise → · Instant USDC / Invoice:
rayxxxnd@oxforddigitals.com
V2 of Offlin33er/qwen25-coder-7b-solidity-audit. Same base model and QLoRA recipe, retrained for 1 epoch on the relabeled Offlin33er/solidity-audit-instruct-v2 dataset: all finding labels normalized into 8 canonical classes (Reentrancy, Arithmetic Error, Access Control Flaw, Input Validation Error, Frontrunning / MEV, Denial of Service (DoS), Business Logic Violation, Clean (No Vulnerability)), with the system prompt rewritten to enforce the closed taxonomy verbatim.
Part of the Solidity Audit Scanner project.
A newer version exists: V3 (verified fallback resolution, best detection F1 0.986). V2 remains the best type-match config.
The V2 test split is the identical code to V1's (split-preserving relabeling), so rates are directly comparable.
| Metric | V1 adapter | V2 adapter |
|---|---|---|
| Detection precision | 1.00 | 0.986 |
| Detection recall | 1.00 | 0.971 |
| False-positive rate on clean | 0.00 | 0.033 (1/30) |
| Finding-type match | 0.30 (lenient substring/keyword) | 0.485 (strict exact canonical match) |
Read honestly:
Full per-row records: eval_results.json.
Training: 139 steps (~69 min on 1× A10G), final loss 0.5489, token accuracy 0.857 —
trackio dashboard.
Identical to V1 except the adapter id; the system prompt must be the V2 taxonomy prompt from the dataset card (the model was trained with it verbatim).
Same as V1 plus: closed 8-class taxonomy trades fine-grained labels for consistency; ~406 rows (16% of vulnerable data) carry default-mapped Business Logic labels. Not a substitute for a professional audit.
Defensive security tooling: analyzes code you paste in. Only audit contracts you are authorized to review.
adapter_model.safetensors 162 MBtraining_args.bin 5.9 kBQwen/Qwen2.5-Coder-7B-Instruct