paperDecember 2025Unreviewed

Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation

Toqeer Ali Syed, M. R. Belgaum, Salman Jan, Asadullah Khan, Saad Said Alqahtani

International Conferences on Computing Advancements

Abstract

Software supply chain attacks increasingly target trusted development and delivery processes, making conventional post-build integrity mechanisms insufficient. Existing frameworks like SLSA, SBOM, and in-toto mainly provide provenance and traceability but cannot actively identify or remove vulnerabilities during production. This paper presents an agentic AI approach for autonomous software supply chain security, combining large language model (LLM) reasoning, reinforcement learning (RL), and mul

Framework mappings

OWASP Top 10 for LLM Applications

LLM03Supply Chain

MITRE ATLAS

AML.T0010AI Supply Chain Compromise

Suggested from the entry's categories.

Cite

@inproceedings{syed2025agentic,
  title = {{Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation}},
  author = {Toqeer Ali Syed and M. R. Belgaum and Salman Jan and Asadullah Khan and Saad Said Alqahtani},
  year = {2025},
  month = dec,
  booktitle = {International Conferences on Computing Advancements},
  eprint = {2512.23480},
  archivePrefix = {arXiv},
  doi = {10.1109/ICCA66035.2025.11430751},
  url = {https://www.semanticscholar.org/paper/7ef12e7f28b538a044f3b2c2af4160446723a200}
}