ArXiv TLDR

CrossCommitVuln-Bench: A Dataset of Multi-Commit Python Vulnerabilities Invisible to Per-Commit Static Analysis

🐦 Tweet
2604.21917

Arunabh Majumdar

cs.CRcs.SE

TLDR

CrossCommitVuln-Bench introduces a dataset of multi-commit Python vulnerabilities that evade per-commit static analysis, highlighting major SAST limitations.

Key contributions

  • Introduces CrossCommitVuln-Bench, a dataset of 15 real-world Python CVEs spanning multiple commits.
  • Reveals 87% of these multi-commit vulnerabilities are invisible to per-commit static analysis tools.
  • Demonstrates even cumulative SAST only detects 27% of cross-commit vulnerabilities.
  • Provides detailed annotations and open-source baselines to foster future research.

Why it matters

Current static analysis tools largely miss vulnerabilities introduced across multiple commits. This paper highlights a critical blind spot, showing 87% of such real-world CVEs are invisible to per-commit SAST. The new dataset and baselines are crucial for developing more effective cross-commit vulnerability detection methods.

Original Abstract

We present CrossCommitVuln-Bench, a curated benchmark of 15 real-world Python vulnerabilities (CVEs) in which the exploitable condition was introduced across multiple commits - each individually benign to per-commit static analysis - but collectively critical. We manually annotate each CVE with its contributing commit chain, a structured rationale for why each commit evades per-commit analysis, and baseline evaluations using Semgrep and Bandit in both per-commit and cumulative scanning modes. Our central finding: the per-commit detection rate (CCDR) is 13% across all 15 vulnerabilities - 87% of chains are invisible to per-commit SAST. Critically, both per-commit detections are qualitatively poor: one occurs on commits framed as security fixes (where developers suppress the alert), and the other detects only the minor hardcoded-key component while completely missing the primary vulnerability (200+ unprotected API endpoints). Even in cumulative mode (full codebase present), the detection rate is only 27%, confirming that snapshot-based SAST tools often miss vulnerabilities whose introduction spans multiple commits. The dataset, annotation schema, evaluation scripts, and reproducible baselines are released under open-source licenses to support research on cross-commit vulnerability detection.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.