Securing agentic AI workflows: A defence-in-depth framework for autonomous systems

Abstract

The rapid enterprise adoption of agentic artificial intelligence (AI) has introduced a category of security risk that existing cyber security frameworks were not designed to address. With 78 per cent of Fortune 500 companies projected to deploy agentic AI by 2026 and the global market expected to reach US$89.6bn, the attack surface created by these autonomous workflows demands urgent attention from security practitioners. This paper examines the distinct threat model presented by agentic AI, dra

Categories

@inproceedings{mahadevaswamy2026securing,
  title = {{Securing agentic AI workflows: A defence-in-depth framework for autonomous systems}},
  author = {Sushma Mahadevaswamy},
  year = {2026},
  month = aug,
  booktitle = {International Conference on Cyber Security And Protection Of Digital Services},
  doi = {10.69554/miwg3713},
  url = {https://www.semanticscholar.org/paper/4e564ab7616c533887366a8634d3e255008bb4f7}
}