Benchmark RadarAI BENCHMARK PROFILE
Vul4Py
Vul4Py evaluates automated vulnerability repair in Python across 100 real vulnerabilities from 60 open-source projects, with paired exploit and functional oracles.
- Released
- 2026-08-01
- Readiness
- Paper only
- Primary field
- Cybersecurity
Why it matters
It addresses the gap of missing functional regression checks in existing Python AVR benchmarks, providing a more reliable comparison of repair methods.
Motivation
Automated Vulnerability Repair (AVR) has advanced rapidly across program analysis, machine learning, and Large Language Models (LLMs), but a verifiable, head-to-head comparison of AVR approaches on Python is still missing.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.