Generative AI, exemplified by models like transformers, has opened up new possibilities in various domains but also raised concerns about fairness, transparency and reliability, especially in fields like medicine and law. This paper emphasizes the urgency of ensuring fairness and quality in these domains through generative AI. It explores using cryptographic techniques, particularly Zero-Knowledge Proofs (ZKPs), to address concerns regarding performance fairness and accuracy while protecting model privacy. Applying ZKPs to Machine Learning models, known as ZKML (Zero-Knowledge Machine Learning), enables independent validation of AI-generated content without revealing sensitive model information, promoting transparency and trust. ZKML enhances AI fairness by providing cryptographic audit trails for model predictions and ensuring uniform performance across users. We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy. We present a series of empirical results studying snarkGPT's scalability and performance to assess the feasibility and challenges of adopting a ZKML-powered approach to capture quality and performance fairness problems in generative AI models.

翻译：生成式AI（以Transformer等模型为代表）在多个领域开辟了新的可能性，但也引发了公平性、透明度和可靠性方面的担忧，尤其在医学和法律等关键领域。本文强调通过生成式AI确保这些领域公平性与质量的紧迫性，探讨利用密码学技术（特别是零知识证明ZKP）解决性能公平性与准确性问题，同时保护模型隐私。将ZKP应用于机器学习模型（即零知识机器学习ZKML），可在不泄露敏感模型信息的情况下独立验证AI生成内容，促进透明度与信任。ZKML通过为模型预测提供加密审计追踪并确保用户间性能一致性来增强AI公平性。我们提出snarkGPT——针对Transformer的实用ZKML实现，使用户能在保护模型隐私的同时验证输出准确性与质量。通过系列实证研究分析snarkGPT的可扩展性与性能，评估采用ZKML方法捕获生成式AI模型质量与性能公平性问题的可行性及挑战。