Bing-Jyue Chen

Email: bjchen4 (at) illinois (dot) edu

I am a 2nd-year PhD student in Computer Science at UIUC. My current research focuses on zero knowledge machine learning (zkml) with Prof. Daniel Kang. I am also interested in privacy-preserving machine learning, and advanced cryptography.

Before that, I was a research assistant in the Institute of Information Science at Academia Sinica, supervised by Prof. De-Nian Yang. I received my B.S. and M.S. in Electrical Engineering and Communication Engineering from National Taiwan University. I have fortunately worked with Prof. Tsungnan Lin on blockchain scalability and anomaly detection in browser fingerprinting networks.

news

Feb 11, 2024	My paper was accepted for European chapter of ACM SIGOPS (EuroSys)!
Dec 23, 2023	My paper was accepted for IEEE International Conference on Data Engineering (ICDE)!
Aug 1, 2023	I leave Academia Sinica and begin my journey to pursue a PhD in UIUC CS.

selected publications

ZKML: An Optimizing System for ML Inference in Zero-Knowledge Proofs

Bing-Jyue Chen, Suppakit Waiwitlikhit, Ion Stoica, and 1 more author

In Proceedings of the Nineteenth European Conference on Computer Systems (EuroSys) Apr 2024

Abs

Machine learning (ML) is increasingly used behind closed systems and APIs to make important decisions. For example, social media uses ML-based recommendation algorithms to decide what to show users, and millions of people pay to use ChatGPT for information every day. Because ML is deployed behind these closed systems, there are increasing calls for transparency, such as releasing model weights. However, these service providers have legitimate reasons not to release this information, including for privacy and trade secrets. To bridge this gap, recent work has proposed using zero-knowledge proofs (specifically a form called ZK-SNARKs) for certifying computation with private models but has only been applied to unrealistically small models. In this work, we present the first framework, ZKML, to produce ZK-SNARKs for realistic ML models, including state-of-the-art vision models, a distilled GPT-2, and the ML model powering Twitter’s recommendations. We accomplish this by designing an optimizing compiler from TensorFlow to circuits in the halo2 ZK-SNARK proving system. There are many equivalent ways to implement the same operations within ZK-SNARK circuits, and these design choices can affect performance by 24×. To efficiently compile ML models, ZKML contains two parts: gadgets (efficient constraints for low-level operations) and an optimizer to decide how to lay out the gadgets within a circuit. Combined, these optimizations enable proving on a wider range of models, faster proving, faster verification, and smaller proofs compared to prior work.