Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries

Abstract

Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protection against attacks from malicious agents. The state-of-the-art solution, SAGA, assumes a logically centralized point of trust, the Provider, which serves as a repository for user and agent information and actively enforces policies. While SAGA provides protection against malicious agents, it remains vulnerable to a mali

Categories

@misc{laws2026attacks,
  title = {{Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries}},
  author = {Matthew D. Laws and Alina Oprea and Cristina Nita-Rotaru},
  year = {2026},
  month = may,
  eprint = {2605.12364},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.12364}
}