GovSecLLM++: A Compliance-Aware Benchmark for Security Testing and Governance Evidence in LLM-Based Applications

Conference contribution listed in HAL; proceedings publication details are not yet verified. SecAI, ESORICS 2026

Yulliwas Ameur; Insaf Imene Lasledj; Samia Bouzefrane; Lyes Khoukhi. "GovSecLLM++: A Compliance-Aware Benchmark for Security Testing and Governance Evidence in LLM-Based Applications." SecAI, ESORICS 2026. HAL: hal-05743323.

BibTeX HAL / texte Code et artefacts

Status: Conference contribution listed in HAL; proceedings publication details are not yet verified.

Conference period: 2026-09. The page date records this listing; it is not a proceedings publication date.

Contribution in brief

GovSecLLM++ connects security testing of LLM applications to inspectable governance evidence. Its public artifact package includes adaptive test outputs, scoring utilities, strict rescoring files, human-validation summaries, a data card and reproducibility notes. The examples use synthetic secrets and credentials.

The software and dataset are separately citable objects. Software DOI · Dataset concept DOI · Dataset version DOI. The current code release does not include the final paper PDF.

Research highlights and scope of the evidence.