Author

Aditya Katkar

h-index 0 View on Semantic Scholar

We have 2 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

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

NiyamAI is presented, an intent bound runtime guardrail architecture providing cryptographically verifiable execution integrity for autonomous agents and subjects its own enforcement mechanism to 18 adversarial vectors across six classes, disclosing two implementation vulnerabilities identified and remediated during development.

Aditya Katkar, Om Karkele, Kartik Mandhane et al. · 1 citation

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

This paper evaluated Niyam-AI on 2,000 real-world agent scenarios from Agent-SafetyBench and compared it against three existing safety approaches: NeMo Guardrails, Meta's Llama Prompt Guard 2, and OpenAI's GPT-OSS-Safeguard.

Aditya Katkar · 0 citations