High Performance Privacy Preserving AI

The ebook edition of this title is Open Access and freely available to read online.

Artificial intelligence (AI) depends on data. In sensitive domains – such as healthcare, security, finance, and many more – there is therefore tension between unleashing the power of AI and maintaining the confidentiality and security of the relevant data.

This book – intended for researchers in academia and R&D engineers in industry – explains how advances in three areas―AI, privacy-preserving techniques, and acceleration―allow us to achieve the dream of high performance privacy-preserving AI. It also discusses applications enabled by this emerging interplay.

The book covers techniques, specifically secure multi-party computation and homomorphic encryption, that provide complexity theoretic security guarantees even with a single data point. These techniques have traditionally been too slow for real-world usage, and the challenge is heightened with the large sizes of today's state-of-the-art neural networks, including large language models (LLMs). This book does not cover techniques like differential privacy that only concern statistical anonymization of data points.

Jayavanth Shenoy develops and integrates sophisticated software solutions for highly advanced, performant, distributed network systems, focusing on acceleration of cryptographic and artificial intelligence applications. He is an expert in privacy-preserving AI and also has extensive experience in high performance computing.

Patrick Grinaway earned his doctorate in the Chodera Lab of the Weill Cornell Medical College of Cornell University. He conducted work on advanced statistical sampling methods for biomedical computation and on distributed computing. He has expertise in artificial intelligence, cryptography, and drug discovery

Shriphani Palakodety holds expertise in machine learning methods, notably for sensitive or difficult-to-access data, and blockchain systems. He has published at top venues in artificial intelligence and natural language processing, including AAAI, EMNLP, and IJCAI. He co-authored the book Low Resource Social Media Text Mining.