Hugging Face's logo

ayshajavd
/
graphcodebert-vuln-classifier

Text Classification
Transformers
Safetensors
English
code
roberta
security
vulnerability-detection
code-analysis
multi-label-classification
graphcodebert
owasp
cwe
static-analysis
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community

GraphCodeBERT Vulnerability Classifier

A multi-label code vulnerability detection model that identifies 31 vulnerability classes (30 CWEs + safe) mapped to the OWASP Top 10 2021 categories. Fine-tuned from CodeBERTa-small-v1 on 175K+ labeled code samples.

Quick Start 

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_id = "ayshajavd/graphcodebert-vuln-classifier"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)
model.eval()

code = """
import sqlite3
def get_user(username):
    query = f"SELECT * FROM users WHERE username = '{username}'"
    conn = sqlite3.connect('db.sqlite')
    return conn.execute(query).fetchone()
"""

inputs = tokenizer(code, return_tensors="pt", max_length=512, truncation=True, padding=True)
with torch.no_grad():
    logits = model(**inputs).logits
    probs = torch.sigmoid(logits).squeeze()

# Get predictions above threshold
TARGET_CWES = ["safe", "CWE-20", "CWE-22", "CWE-78", "CWE-79", "CWE-89", "CWE-94",
    "CWE-119", "CWE-125", "CWE-190", "CWE-200", "CWE-264", "CWE-269", "CWE-276",
    "CWE-284", "CWE-287", "CWE-310", "CWE-327", "CWE-330", "CWE-352", "CWE-362",
    "CWE-399", "CWE-401", "CWE-416", "CWE-434", "CWE-476", "CWE-502", "CWE-601",
    "CWE-787", "CWE-798", "CWE-918"]

threshold = 0.5
for i, (cwe, prob) in enumerate(zip(TARGET_CWES, probs)):
    if prob > threshold:
        print(f"{cwe}: {prob:.3f}")

Model Details

Property Value
Architecture RobertaForSequenceClassification (6 layers, 768 hidden, 83.5M params)
Base Model CodeBERTa-small-v1
Task Multi-label classification (BCEWithLogitsLoss with class weights)
Labels 31 (30 CWE categories + "safe")
Max Sequence Length 512 tokens
Recommended Threshold 0.5 (balanced precision/recall) or 0.3 (high recall, security-first)

Supported Languages

Python, JavaScript, Java, C, C++, PHP, Go

The model was trained on a diverse multi-language dataset. Performance is strongest on C/C++ (largest training subset from BigVul) and Python/JavaScript (from the multi-language datasets).

Evaluation Results (Test Set — 5,000 samples)

Threshold Comparison

Threshold Macro F1 Micro F1 Weighted F1 Macro Precision Macro Recall
0.2 0.066 0.301 0.859 0.048 0.562
0.3 0.081 0.458 0.865 0.057 0.502
0.4 0.101 0.626 0.870 0.070 0.439
0.5 0.125 0.739 0.870 0.088 0.366

Per-Class Performance (threshold=0.3)

OWASP A01:2021 — Broken Access Control

CWE Name Support Precision Recall F1
CWE-22 Path Traversal 2 0.000 0.000 0.000
CWE-200 Information Exposure 30 0.063 0.800 0.117
CWE-264 Permissions/Privileges 23 0.025 0.696 0.049
CWE-269 Improper Privilege Mgmt 1 0.000 0.000 0.000
CWE-276 Incorrect Permissions 0 — — —
CWE-284 Access Control 5 0.000 0.000 0.000
CWE-352 CSRF 1 0.000 0.000 0.000
CWE-601 Open Redirect 0 — — —

OWASP A02:2021 — Cryptographic Failures

CWE Name Support Precision Recall F1
CWE-310 Cryptographic Issues 5 0.000 0.000 0.000
CWE-327 Broken Crypto Algorithm 1 0.000 0.000 0.000
CWE-330 Insufficient Randomness 1 0.000 0.000 0.000

OWASP A03:2021 — Injection

CWE Name Support Precision Recall F1
CWE-20 Input Validation 69 0.023 0.957 0.046
CWE-78 Command Injection 1 0.011 1.000 0.021
CWE-79 XSS 16 0.084 0.750 0.151
CWE-89 SQL Injection 15 0.096 1.000 0.174
CWE-94 Code Injection 27 0.123 1.000 0.220
CWE-119 Buffer Overflow 118 0.088 0.898 0.160
CWE-125 Out-of-bounds Read 35 0.048 0.829 0.091
CWE-190 Integer Overflow 14 0.033 1.000 0.064
CWE-401 Memory Leak 2 0.022 1.000 0.044
CWE-416 Use After Free 20 0.048 0.400 0.086
CWE-476 NULL Pointer Deref 30 0.032 0.867 0.061
CWE-787 Out-of-bounds Write 46 0.052 0.891 0.099

OWASP A04:2021 — Insecure Design

CWE Name Support Precision Recall F1
CWE-362 Race Condition 11 0.035 0.636 0.065
CWE-399 Resource Management 21 0.008 0.857 0.015
CWE-434 File Upload 0 — — —

OWASP A07–A10

CWE Name Support Precision Recall F1
CWE-287 Authentication 0 — — —
CWE-798 Hardcoded Credentials 0 — — —
CWE-502 Deserialization 10 0.056 1.000 0.106
CWE-918 SSRF 0 — — —

Key Metric: Safe Code Detection

Class Support Precision Recall F1
safe 4,496 0.927 0.975 0.950

Model Strengths

  • Excellent recall on many vulnerability classes (0.75–1.0 for SQL injection, buffer overflow, XSS, code injection, etc.)
  • Strong safe code detection (F1=0.95) — reliably identifies secure code
  • High sensitivity — at threshold 0.3, catches most real vulnerabilities (macro recall=0.50)

Model Limitations

  • Low precision on rare classes — many false positives, especially on CWEs with few training examples
  • Precision can be improved by using threshold=0.5 (macro F1 improves to 0.125 but recall drops)
  • Classes with 0 test support cannot be evaluated

Design choice: For security applications, we prioritize recall (catching real vulnerabilities) over precision (reducing false positives). Missing a real vulnerability (false negative) is worse than flagging safe code (false positive).

Training Data

The model was trained on the code-security-vulnerability-dataset (175,419 samples), combining:

  1. BigVul — 265K C/C++ vulnerable functions from real CVEs
  2. CWE-enriched BigVul/PrimeVul — Balanced CWE-labeled subset
  3. Code Vulnerability Labeled — Multi-language (Python, JS, Java, PHP, Go)
  4. CyberNative DPO — Vulnerable/secure code pairs

Training Configuration

Parameter Value
Epochs 2
Batch Size 8
Learning Rate 5e-5
Scheduler Cosine with warmup (50 steps)
Loss BCEWithLogitsLoss (class-weighted, pos_weight clipped to 30x)
Training Subset 20K balanced samples
Optimizer AdamW (fused)

Limitations

  1. Class imbalance: Many rare CWE types have very few training examples, leading to high false positive rates
  2. Sequence length: Limited to 512 tokens — long functions may be truncated
  3. Language bias: Strongest on C/C++ due to BigVul's dominance. Go and PHP performance may be lower
  4. Single-function analysis: Analyzes individual functions, not cross-function or cross-file vulnerabilities
  5. Not a replacement: Should complement manual review and established SAST tools (Semgrep, CodeQL, etc.)

Interactive Demo

Try the model in our Code Security Analyzer Space — paste any code and get a full security report with OWASP mapping, severity scores, attack chain analysis, and suggested fixes.

Citation 

@misc{graphcodebert-vuln-classifier,
  title={GraphCodeBERT Vulnerability Classifier: Multi-label CWE Detection Mapped to OWASP Top 10},
  author={ayshajavd},
  year={2025},
  url={https://huggingface.co/ayshajavd/graphcodebert-vuln-classifier}
}
Downloads last month
61
Safetensors
Model size
83.5M params
Tensor type
F32
·
Inference Providers NEW
Text Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ayshajavd/graphcodebert-vuln-classifier

Base model

huggingface/CodeBERTa-small-v1
Finetuned
(69)
this model

Datasets used to train ayshajavd/graphcodebert-vuln-classifier

Space using ayshajavd/graphcodebert-vuln-classifier 1

Evaluation results