Me
I am a technology leader, applied scientist, cryptographer, focusing on real-world security & privacy problems and its intersection to AI/ML. I build and lead high-performing teams working on problems that impact this world. I maintain my academic interests, but I am more passionate about bringing advanced tech to real problems, not hypothetical ones. I obtained my Ph.D. in Computer Science at Boston University.
I recently spend a lot time of building the next-gen trustworthy and efficent AI computing infra. Previously, I have been working as a leading scientist & tech leader at Amazon Web Service, Facebook(Meta), Apple Inc, Robinhood, etc. My past research has generally focused on developing privacy-preserving technologies and trusted AI tools.
(Oh, I sometimes go by Jery if you would like :)
I'm exploring new frontiers in building the next-gen computing in AI. News: Brewing something new! Stay tuned!
My Works
My Erdős number is 3. I investigate how humans can benefit from technological advancements and how we can let cooler and more advanced technologies gain massive adoption.
- Our article on building the trustworthy and secure computing for AGI.
- Here is a article I wrote about MPC in crypto custody.
- My blog post on Amazon.scienceMachine learning models that act on encrypted datatalks about a joint work with Prof. Joan Feigenbaum. Open-source code can be found on GitHub.
I investigate the following these days:
ML/AI
Developing Robust and Generalizable Trustworthy AI. AI systems that generalize across domains, creating reliable intelligence that seamlessly integrates into daily life.
Security / Cryptography
Making Our Digital World Safer and Better. Enhancing Digital Trust Through Cryptographic and Trusted Computing. Guarantees and rebuild user privacy and trust in digital infrastructure.
Patents
Data Sharing Methods
X. Meng, MJ Campagna • US Patent 11,599,655 • 2023
Multi-party analysis of streaming data with privacy assurances
NA Allen, X Meng • US Patent 11,328,087 • 2022
System and method for processing encrypted search
N Allen, MJ Campagna, XJ Meng • US Patent 11,023,595 • 2021
Secure join protocol in encrypted databases
XJ Meng • US Patent US10929402B1 • 2020
Selected Publications
A Secure and Scalable Federated Learning Framework without Trusted Aggregators
EMNLP 2021
Variance of the Gradient Also Matters: Privacy Leakage from Gradients
IEEE WCCI 2022 (IJCNN 2022)
Computational Fuzzy Extractors
with Ben Fuller, and Leo Reyzin • Information and Computation
Privacy-Preserving Hierarchical Clustering: Formal Security and Efficient Approximation
with Dimitrios Papadopoulos, Alina Oprea, Nikos Triandopoulos • ACM CCSW Cloud Computing Workshop 2021
Privacy-preserving XGBoost Inference
X Meng, J Feigenbaum • PPML at NeurIPS 2020
Top-k Query Processing on Encrypted Databases with Strong Security Guarantees
with Haohan Zhu, George Kollios • 34th IEEE ICDE 2018
NED: An Inter-Graph Node Metric based on Edit Distance
with Haohan Zhu, George Kollios • PVLDB 10(6):697-708, 2017
GRECS: Approximate Shortest Distance Queries on Encrypted Graphs
with Seny Kamara, Kobbi Nissim, and George Kollios • 22nd ACM CCS 2015
Privacy-Preserving Similarity Evaluation of Time Series Data
with Haohan Zhu, and George Kollios • 17th EDBT/ICDT 2014
Computational Fuzzy Extractors
with Ben Fuller, and Leo Reyzin • 19th IACR ASIACRYPT 2013