Text Generation
PEFT
Safetensors
English
lora
qlora
vulnerability-detection
security
cwe
llvm-ir
code
Instructions to use phazertron/vulnerability-detector-ir-source with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use phazertron/vulnerability-detector-ir-source with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from phazertron/vulnerability-detector-ir-source: direct link, hf CLI and curl.
- Browser
- Download file 4.23 kB
-
https://huggingface.co/phazertron/vulnerability-detector-ir-source/resolve/main/README.md
- Command line
-
hf download hf://phazertron/vulnerability-detector-ir-source/README.md
-
curl -L -o README.md https://huggingface.co/phazertron/vulnerability-detector-ir-source/resolve/main/README.md
4.23 kB
| library_name: peft | |
| pipeline_tag: text-generation | |
| tags: | |
| - lora | |
| - qlora | |
| - peft | |
| - vulnerability-detection | |
| - security | |
| - cwe | |
| - llvm-ir | |
| - code | |
| language: | |
| - en | |
| base_model: | |
| - Qwen/Qwen2.5-Coder-7B-Instruct | |
| license: apache-2.0 | |
| # Vulnerability Detector — IR vs source adapters (Phase 3B) | |
| > **Status: valid research artifacts.** Both adapters are functional, but their | |
| > purpose is to reproduce the one genuine positive finding of the thesis | |
| > (Section 16): training on LLVM IR detects worse yet classifies the CWE far | |
| > better than training on the matched C source. Use them to reproduce that | |
| > dissociation, not as a general detector. | |
| From the MSc thesis *Software Vulnerability Detection with Advanced Machine | |
| Learning Techniques* (Claudio Bendini, University of Parma, 2025–2026, advisor | |
| Prof.ssa Eleonora Iotti). Both adapters fine-tune the same base model, | |
| Qwen2.5-Coder-7B-Instruct, on the same SARD Juliet programs, one arm on the C | |
| source and the other on the `clang -O0 -emit-llvm` intermediate representation. | |
| - **Code, data pipeline, full results:** https://github.com/Phazertron/Vulnerability_Detector | |
| - **Canonical record:** [`docs/EXPERIMENT_LOG.md`](https://github.com/Phazertron/Vulnerability_Detector/blob/main/docs/EXPERIMENT_LOG.md), Section 16. | |
| - **Companion repos:** [Phase 2 SFT](https://huggingface.co/phazertron/vulnerability-detector-sft) (working detectors) and [DPO](https://huggingface.co/phazertron/vulnerability-detector-dpo-negative) (a negative result). | |
| ## The finding | |
| On the parity split (246 records both arms could handle): | |
| | Metric | `source` arm | `ir` arm | Gap | | |
| |---|---|---|---| | |
| | Binary F1 (detection) | 0.5069 | 0.3116 | -0.1954 | | |
| | CWE accuracy given detection | 0.1455 | **0.7742** | **+0.6287** | | |
| Restricted to the 11 records both arms detected correctly, CWE accuracy is | |
| 1/11 for source against 8/11 for IR (McNemar exact p = 0.039; 95% CI on the gap | |
| [+0.18, +1.00], excludes zero). IR is **worse at deciding whether code is | |
| vulnerable** and **much better at naming which weakness it is**, and the | |
| defensible claim is the +0.18 lower bound, not the point estimate. The effect | |
| spreads across 13 CWEs rather than concentrating on memory-safety ones. | |
| ## The adapters | |
| | Subfolder | Trained on | Role | | |
| |---|---|---| | |
| | `ir` | SARD Juliet, LLVM IR | the IR arm (strong CWE attribution) | | |
| | `source` | SARD Juliet, C source | the matched baseline for comparison | | |
| Both are for reproducing Section 16. Neither is a strong real-world detector: | |
| they are trained on synthetic Juliet programs and do not transfer to real-world | |
| code (Section 14). | |
| ## How to load | |
| Both use base `Qwen/Qwen2.5-Coder-7B-Instruct`. Rank 32, alpha 64, dropout 0.05, | |
| all attention and MLP projections, 4-bit base (QLoRA), 2048-token sequence | |
| budget. PEFT 0.13.2, TRL 1.5.0, Transformers 4.57.6. | |
| ```python | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig | |
| from peft import PeftModel | |
| base_id = "Qwen/Qwen2.5-Coder-7B-Instruct" | |
| repo = "phazertron/vulnerability-detector-ir-source" | |
| sub = "ir" # or "source" | |
| bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", | |
| bnb_4bit_compute_dtype=torch.bfloat16) | |
| tok = AutoTokenizer.from_pretrained(repo, subfolder=sub) | |
| base = AutoModelForCausalLM.from_pretrained(base_id, quantization_config=bnb, device_map="auto") | |
| model = PeftModel.from_pretrained(base, repo, subfolder=sub) | |
| ``` | |
| The `source` arm is prompted with the C function; the `ir` arm with the | |
| function's LLVM IR (see the pipeline in the GitHub repo). Expected output is one | |
| line: `VULNERABLE: CWE-787` or `CLEAN`. | |
| ## Training data | |
| [SARD Juliet](https://samate.nist.gov/SARD/test-suites/112) (compilable | |
| synthetic C). The adapters contain learned weights, not dataset content. | |
| ## Licensing | |
| Both adapters derive from Qwen2.5-Coder-7B-Instruct and are released under | |
| [Apache 2.0](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE). | |
| ## Citation | |
| ```bibtex | |
| @mastersthesis{bendini2026vulndetect, | |
| author = {Claudio Bendini}, | |
| title = {Software Vulnerability Detection with Advanced Machine Learning Techniques}, | |
| school = {University of Parma}, | |
| year = {2026} | |
| } | |
| ``` | |