# Neural Interactive Proofs

arXiv: https://arxiv.org/abs/2412.08897 · HTML: https://mlsanity.com/paper/2412.08897/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 16 of 16)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Knockoff Nets: Stealing Functionality of Black-Box Models](https://mlsanity.com/paper/1812.02766/) (2018)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Proof-of-Learning: Definitions and Practice](https://mlsanity.com/paper/2103.05633/) (2021)
- [Introduction to Neural Network Verification](https://mlsanity.com/paper/2109.10317/) (2021)
- [Scalable AI Safety via Doubly-Efficient Debate](https://mlsanity.com/paper/2311.14125/) (2023)
- [SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud](https://mlsanity.com/paper/1706.10268/) (2017)
- [Managing extreme AI risks amid rapid progress](https://mlsanity.com/paper/2310.17688/) (2023)
- [Differentiable Game Mechanics](https://mlsanity.com/paper/1905.04926/) (2019)
- [Machine Learning Model Sizes and the Parameter Gap](https://mlsanity.com/paper/2207.02852/) (2022)
- [Learning to Give Checkable Answers with Prover-Verifier Games](https://mlsanity.com/paper/2108.12099/) (2021)
- [Modeling Precomputation In Games Played Under Computational Constraints](https://mlsanity.com/paper/2105.09145/) (2021)

## Built on by (most cited first, 7 of 7)

- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Avoiding Obfuscation with Prover-Estimator Debate](https://mlsanity.com/paper/2506.13609/) (2025)
- [Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction](https://mlsanity.com/paper/2605.25133/) (2026)
- [How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs](https://mlsanity.com/paper/2607.03561/) (2026)
- [Bayesian Decision Making around Experts](https://mlsanity.com/paper/2510.08113/) (2025)
- [Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency](https://mlsanity.com/paper/2609.24895/) (2026)
- [How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate](https://mlsanity.com/paper/2610.02557/) (2026)

## Abstract (arXiv)

We consider the problem of how a trusted, but computationally bounded agent (a 'verifier') can learn to interact with one or more powerful but untrusted agents ('provers') in order to solve a given task. More specifically, we study the case in which agents are represented using neural networks and refer to solutions of this problem as neural interactive proofs. First we introduce a unifying framework based on prover-verifier games, which generalises previously proposed interaction protocols. We then describe several new protocols for generating neural interactive proofs, and provide a theoretical comparison of both new and existing approaches. Finally, we support this theory with experiments in two domains: a toy graph isomorphism problem that illustrates the key ideas, and a code validation task using large language models. In so doing, we aim to create a foundation for future work on neural interactive proofs and their application in building safer AI systems.