Hideaki Takahashi

I am a first-year PhD student in Computer Science department at Columbia University, advised by Prof. Junfeng Yang. I also work closely with Prof. Suman Jana and am a member of the Center for Digital Finance and Technologies. My current work focuses on Software Security and Zero Knowledge Proofs.

I received a Bachelor of Arts and Science in Informatics from the University of Tokyo, where I was advised by Prof. Alex Fukunaga, focusing on privacy-preserving AI planning. During my undergraduate studies, I spent a gap year as a research intern at Tsinghua University under the supervision of Prof. Yang Liu and Prof. Jingjing Liu, investigating security vulnerabilities in Federated Learning.

I am also passionate about open-source development. My project, AIJack, which aims to attack, defend, and debug machine learning models, has gained traction with over 300 stars on GitHub and has been widely used in research.

Education

Columbia University in the City of New York: Sep. 2024 ~
Ph.D. Student (Computer Science)
The University of Tokyo: Apr. 2019 ~ Mar. 2024
Bachelor of Arts and Science (Informatics)

Papers (peer-reviewed)

[AAMAS'24] On the Transit Obfuscation Problem. Proceedings of the International Conference on Autonomous Agents and Multi-Agent Systems - 2024
Hideaki Takahashi*, Alex Fukunaga
[ICLR'24] VFLAIR, A Research Library and Benchmark for Vertical Federated Learning. Proceedings of the International Conference on Learning Representations - 2024
Zou, Tianyuan, Zixuan Gu, Yuanqin He, Hideaki Takahashi, Yang Liu, Guangnan Ye and Ya-Qin Zhang
[CVPR'23] Breaching FedMD, Image Recovery via Paired-Logits Inversion Attack. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition - 2023
Hideaki Takahashi*, Jingjing Liu, and Yang Liu

Preprints

Detecting buggy contracts via smart testing. arXiv:2409.04597 - 2024
Sally Junsong Wang, Jianan Yao, Kexin Pei, Hideaki Takahashi, and Junfeng Yan
Eliminating Label Leakage in Tree‑based Vertical Federated Learning. arXiv:2307.10318 - 2023
Hideaki Takahashi*, Jingjing Liu, and Yang Liu
Difficulty of Detecting Overstated Dataset Size in Federated Learning. Technical Report of DPS, 10, Information Processing Society of Japan. - 2021
Hideaki Takahashi*, Kohei Ichikawa, and Keichi Takahashi

Softwares

AIJack

Security risk simulator for machine learning (more than 300 stars on GitHub and used in 8 papers)
MyZKP

Building Zero Knowledge Proof from Scratch in Rust
rhoevm

Symbolic EVM execution engine written in Rust to find vulnerabilities within Ethereum smart contracts
Gymbo

Symbolic execution engine using gradient descent to solve path constraints

Research Experience

Fukunaga Lab, The University of Tokyo: Apr. 2023 - Mar. 2024
Undergraduate Student
Conducted research on the transit obfuscation problem, which is a new task of privacy-preserving AI planning, under the supervision of Prof. Alex Fukunaga.
Institute for AI Industry Research, Tsinghua University: Jan. 2022 ‑ Feb. 2023
Federated Learning & Privacy Computing Intern
Conducted research on federated learning and privacy computing under the supervision of Prof. Yang Liu and Prof. Jingjing Liu.
Laboratory for Software Design and Analysis, Nara Institute of Science and Technology: Aug. 2021 ‑ Sep. 2021
Visiting Student
Conducted research on the free‑rider problem of federated learning under the supervision of Prof. Kohei Ichikawa and Prof. Keichi Takahashi.

Industry Experience

Apple Inc.: Feb. 2024 - Jul. 2024
Technical Internship: AIML/Software Engineer
Working on AIML/software engineering.
UTokyo Economic Consulting Inc.: Oct. 2020 - Mar. 2024
Research Assistant
Working on research and social implementations of econometrics and machine learning.
RECRUIT: Aug. 2020 - Sep. 2020
Data Science Intern
Worked on a location‑based restaurant recommendation iOS app.
M3, Inc.: Feb. 2020 - Jun. 2020
Data Analysis Intern
Worked on a data analysis project in the field of medical surveys.
FRONTEO, Inc.: Sep. 2019 ‑ Mar. 2020
Research Intern
Worked on the detection of anomaly documents with NLP and network analysis.

Honors

Funai Foundation Scholarship - 2024
Scholarship
Granted two years of tuition and stipend
Kaggle, Google - Fast or Slow? Predict AI Model Runtime - 2023
45th/616 teams (silver medal)
Compiler Optimization, Automated Algorithmic Configuration
Kaggle, Hungry Geese - 2021
67th/875 teams (bronze medal)
AI Agent, Reinforcement Learning
Kaggle, Santa 2020 - 2021
52nd/788 teams (bronze medal)
AI Agent, Reinforcement Learning, Multi-Armed Bandit
Kaggle, Google Research Football with Manchester City F.C. - 2020
51st/1138 teams (silver medal)
AI Agent, Reinforcement Learning
Kaggle, Cornell Birdcall Identification - 2020
88th/1390 teams (bronze medal)
Audio Classification, Signal Processing

Service

Reviewer

IEEE Transactions on Network Science and Engineering (Impact Factor: 6.7)
IEEE Transactions on Medical Imaging (Impact Factor: 10.0)

OSS Contributor

PySyft: Platform for secure and private Deep Learning
Nebula: Distributed graph database

Favorite Japanese Restaurants in New York

Okatte Tanto NY, 249 E 49th St New York, NY 10017
Kimura, 31 St Marks Pl, New York, NY 10003
Afuri, 61 N 11th St, Brooklyn, NY 11249
heno heno, 358 W 46th St, New York, NY 10036