NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs

Abstract

Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it shouldn't. Prompt injection, hallucinated reasoning, and unsafe tool calls form the primary attack surface for autonomous LLM agents. Existing defenses rely on software checks like system prompts or policy filters running on the same machine the attacker targets, offering no verifiable proof of execution. We introduce Niyam-AI, a framework that makes s

Categories

Framework mappings

Suggested from the entry's categories.

@misc{katkar2026niyamai,
  title = {{NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs}},
  author = {Aditya Katkar and Om Karkele and Kartik Mandhane and Manisha More and Yash Kashid},
  year = {2026},
  month = aug,
  eprint = {2608.07167},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.07167}
}