ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks

2025-08-16

AI Summary

To address the challenge of simultaneously preserving structural privacy and ensuring multi-dimensional verification credibility in molecular toxicity repair, this work introduces zero-knowledge proofs (ZKPs) to the domain for the first time, proposing the first structure-private zero-knowledge verification framework. Methodologically, we design a unified evaluation circuit compatible with both classification and regression tasks, integrating Poseidon hash-based commitments and a nullifier-based mechanism to prevent replay attacks, enabling end-to-end privacy-preserving verification. Experiments demonstrate that the framework efficiently and securely verifies multi-dimensional toxicity repair metrics—even when molecular SMILES strings and graph structures are fully hidden—while maintaining reasonable circuit size and controllable verification overhead. This work establishes the first provably secure, verifiably trustworthy, and privacy-preserving evaluation paradigm for generative molecular design.

Technology Category

• Machine Learning: Privacy
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In recent years, generative artificial intelligence (GenAI) has demonstrated remarkable capabilities in high-stakes domains such as molecular science. However, challenges related to the verifiability and structural privacy of its outputs remain largely unresolved. This paper focuses on the task of molecular toxicity repair. It proposes a structure-private verification framework - ToxiEval-ZKP - which, for the first time, introduces zero-knowledge proof (ZKP) mechanisms into the evaluation process of this task. The system enables model developers to demonstrate to external verifiers that the generated molecules meet multidimensional toxicity repair criteria, without revealing the molecular structures themselves. To this end, we design a general-purpose circuit compatible with both classification and regression tasks, incorporating evaluation logic, Poseidon-based commitment hashing, and a nullifier-based replay prevention mechanism to build a complete end-to-end ZK verification system. Experimental results demonstrate that ToxiEval-ZKP facilitates adequate validation under complete structural invisibility, offering strong circuit efficiency, security, and adaptability, thereby opening up a novel paradigm for trustworthy evaluation in generative scientific tasks.

Problem

• Ensures verifiability of molecular toxicity repair without revealing structures
• Introduces zero-knowledge proofs for private molecular evaluation
• Develops efficient circuits for secure classification and regression tasks

Innovation

• Zero-knowledge proof for molecular verification
• Poseidon-based commitment hashing system
• Nullifier-based replay prevention mechanism