The rapid expansion of the Internet of Things (IoT) has introduced significant challenges in data authentication, necessitating a balance between scalability and security. Traditional approaches often rely on third parties, while blockchain-based solutions face computational and storage bottlenecks. Our novel framework employs edge aggregating servers and Ethereum Layer 2 rollups, offering a scalable and secure IoT data authentication solution that reduces the need for continuous, direct interaction between IoT devices and the blockchain. We utilize and compare the Nova and Risc0 proving systems for authenticating batches of IoT data by verifying signatures, ensuring data integrity and privacy. Notably, the Nova prover significantly outperforms Risc0 in proving and verification times; for instance, with 10 signatures, Nova takes 3.62 s compared to Risc0’s 369 s, with this performance gap widening as the number of signatures in a batch increases. Our framework further enhances data verifiability and trust by recording essential information on L2 rollups, creating an immutable and transparent record of authentication. The use of Layer 2 rollups atop a permissionless blockchain like Ethereum effectively reduces on-chain storage costs by approximately 48 to 57 times compared to direct Ethereum use, addressing cost bottlenecks efficiently.

Integrating third-party Machine Learning (ML) models into industrial Operational Technology (OT) creates a procurement deadlock: operators cannot verify vendor performance claims without exposing sensitive operational data, while vendors refuse to reveal proprietary model weights before purchase, rendering traditional safeguards such as Non-Disclosure Agreements technically unenforceable. This paper introduces a framework combining Zero Knowledge Proofs (ZKPs) with smart contracts to enable trust-minimized, privacy-preserving competitive model procurement in Industrial Cyber-Physical Systems (ICPS). Our framework allows vendors to cryptographically prove that their model outperforms a legacy baseline without disclosing proprietary weights, a process we term cryptographic performance attestation . The on-chain workflow combines escrow-backed procurement, automated proof verification, and best-vendor selection with arbiter-based dispute resolution. We analyze three distinct ZKP workflow variations for industrial suitability and evaluate their performance on consumer-grade hardware, achieving proving times of approximately three seconds and sub-dollar on-chain verification costs under Layer-2 fee assumptions for the recommended single-proof variation. Results demonstrate the feasibility of pre-deployment model verification while identifying computational trade-offs of recursive proof aggregation. The entire verification phase operates offline with no impact on real-time OT control paths, bridging the IT/OT pre-transaction trust gap while deferring artifact deployment to existing OT tooling.

Integrating third-party Machine Learning (ML) models into industrial Operational Technology (OT) creates a procurement deadlock: operators cannot verify vendor performance claims without sharing representative evaluation data with vendors, while vendors refuse to reveal proprietary model weights before purchase, rendering traditional safeguards such as Non-Disclosure Agreements technically unenforceable. This paper introduces a framework combining Zero-Knowledge Proofs (ZKPs) with smart contracts to enable trust-minimized, cryptographically verifiable competitive model procurement in Industrial Cyber-Physical Systems (ICPS). Vendors cryptographically prove that their model outperforms a legacy baseline without disclosing proprietary weights, a process we term cryptographic performance attestation, while the on-chain workflow automates escrow, proof verification, and best-vendor selection with arbiter-based dispute resolution. ZKP privacy is scoped to vendor model weights; operator-side evaluation-data confidentiality is managed separately via synthetic, de-identified, or public benchmark data. We analyze three ZKP workflow variations and evaluate them on consumer-grade hardware, achieving proving times of approximately three seconds and sub-dollar on-chain verification costs under Layer-2 fee assumptions for the recommended single-proof variation, while identifying computational trade-offs of recursive proof aggregation. The entire verification phase operates offline with no impact on real-time OT control paths, bridging the IT/OT pre-transaction trust gap while deferring artifact deployment to existing OT tooling.