Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap

Abstract

Multi-agent AI platforms move quickly from staging to production, but the way agents establish trust remains rudimentary: an agent either transmits raw data to a peer or accepts that peer's natural-language self-report that a value complies with policy. The first over-shares; the second is unverifiable and is exactly the channel prompt injection attacks. Prevailing responses emphasise identity, visibility, and post-hoc detection, and recent proposals for cryptographically enforced agent policy h

Categories

Framework mappings

Suggested from the entry's categories.

@misc{gopalakrishna2026zeroknowledge,
  title = {{Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap}},
  author = {Ashok Subbabhatta Gopalakrishna},
  year = {2026},
  month = aug,
  eprint = {2608.30083},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.30083}
}