TrustPatch-X: Multi-Stage Explainable Framework for Reliable LLM Patch Validation

Large Language Models (LLMs) have shown strong potential in automated vulnerability repair; however, generated security patches often lack reliability, semantic guarantees, and interpretability. Purely generative approaches may remove super-ficial patterns while failing to eliminate root-cause vulnerabilities or preserve program behavior. To address this limitation, this study proposes an Explainable Multi-Stage Validation Frame-work that integrates static vulnerability filtering, graph-based semantic consistency analysis, and test-driven verification within a unified pipeline. The framework further incorporates a structured explanation module to provide interpretable reasoning for patch correctness. Experimental evaluation on Juliet, Devign, and Defects4J security benchmarks demonstrates that the proposed approach achieves 96.3% vulnerability removal accuracy and reduces false-fix rates to 9.3%, outperforming LLM-only and hybrid baselines. Additionally, the framework maintains high semantic similarity (0.97) and explanation fidelity above 90%while preserving computational efficiency. The results indicate that combining neural generation with structured validation significantly enhances the trustworthiness of AI-driven security patch validation systems.

@article{Parate2026,
  title     = {TrustPatch-X: Multi-Stage Explainable Framework for Reliable LLM Patch Validation},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {4},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Sheetal Madhukar Parate and Jasmine Selvakumari Jeya I},
  doi       = {10.14569/IJACSA.2026.0170487},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170487}
}