Polyhedra Introduces a Breakthrough in AI Trust Infrastructure

"zkPyTorch gives AI agents an identity," said Tiancheng Xie, co-founder of Polyhedra Network. "It's a trusted and scalable way to guarantee the integrity of an AI agent — without rewriting your AI stack," Xie added.

Making Proofs Practical for Machine Learning

Until now, bringing zero-knowledge proofs (ZKPs) to deep learning required bespoke models and custom logic. zkPyTorch removes that barrier, integrating directly with standard PyTorch workflows and outputting circuits ready for ZKP engines like Expander, the world's fastest prover, created by Polyhedra.

Through a novel compilation pipeline — spanning structured graph preprocessing, ZK-friendly quantization, and multi-level circuit optimization — zkPyTorch converts real-world models into field-efficient circuits that preserve performance and accuracy.

Key Benchmarks:

AI You Can Trust, Without Compromising Confidentiality

zkPyTorch is built to facilitate verifiability of both open-source and proprietary models. It ensures that inference correctness is cryptographically verifiable and enables the proof and result to be shared publicly.

This unlocks powerful use cases where AI is responsible for critical decisions, actions, and predictions, including:

Developer-First by Design

zkPyTorch integrates seamlessly into developers' existing PyTorch workflows by:

SDKs are available in Python and Rust, with full docs and example integrations to get developers up and running quickly.

Read zkPyTorch Now

zkPyTorch is part of Polyhedra's broader zkML and verifiable AI initiatives, delivering modular zero-knowledge infrastructure for real-world systems.

Read the full research paper: https://eprint.iacr.org/2025/535.

About Polyhedra

Polyhedra is building foundational infrastructure for trust and scalability in AI and blockchain, systems enabling secure, verifiable, and high-performance applications. Led by a world-class team of engineers, researchers, and business leaders from institutions including UC Berkeley, Stanford, and Tsinghua University, Polyhedra's deep expertise in zero-knowledge proofs and distributed systems underpins the development of our technical solutions that will help form the AI infrastructure of the future.

View original content:https://www.prnewswire.co.uk/news-releases/polyhedra-introduces-a-breakthrough-in-ai-trust-infrastructure-302411438.html