cs.CRNov 18, 2026

Mitigating fix reversal: Counterfactual constraints for function-level vulnerability detection

Authors: Yun Bian, Shihao Li, Haiquan Wang, Yi Chen, Zhao Yang, Zhe Cui

Organizations: Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu, China · University of Chinese Academy of Sciences, Beijing, China

Abstract

Function-level vulnerability detectors often exhibit fix reversal, assigning a higher vulnerability probability to a fixed version than to its vulnerable counterpart. Fixes usually lengthen functions, and larger length increases are associated with more severe reversal. Code-transformation experiments indicate that fix reversal mainly stems from a length shortcut: vulnerability probability increases with function length when content is fixed. We propose CFVul to address this problem. Sliding-window encoding covers complete functions, retaining fix information beyond the truncation boundary. During training, a content constraint encourages the vulnerable version to receive a higher vulnerability probability under a common length input. During inference, a length constraint averages vulnerability probabilities over fixed reference lengths, reducing the influence of actual length changes. On PrimeVul, CFVul achieves a fix-pair ranking metric, PairRank, of 59.4%, exceeding the existing methods compared. For fixes that increase function length by more than 15%, PairRank rises from CodeBERT's 25.8% to 48.4%. PairRank also improves in experiments with four additional models and three additional datasets. By weakening the length shortcut, CFVul reduces cases in which fixed versions receive higher vulnerability probabilities than vulnerable versions. It requires only existing fix pairs and applies to multiple pretrained code models, facilitating adoption in existing detectors.

Explore similar work

CardsList
  1. Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

    May 13, 2026Nils Loose, Joseph Bienhüls, Kristoffer Hempel +2Software Vulnerability DetectionSoftware Engineering Benchmarks

  2. Found, but Not Fixed : From Software Vulnerability Discovery to Fixes with Iterative LLM Pipelines

    Nov 15, 2026Youssef Gamal, Mohamad Fakih, Halima Bouzidi +5Automated Program RepairLLM Self-Correction

  3. VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence

    Oct 4, 2026Leizhen Zhang, Sheng ChenSoftware Vulnerability Detection