Kazuki Iwahana

According to our database, Kazuki Iwahana authored at least 12 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Backdoor Attacks by Leveraging Latent Representation in Competitive Learning for Resistance to Removal.

Kazuki Iwahana, Naoto Yanai, Atsuo Inomata, Toru Fujiwara

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2025

Efficient Privacy-Preserving Data Annotation via Active PrivBayes Synthetic Data Generation.

Osamu Saisho, Takayuki Miura, Kazuki Iwahana, Masanobu Kii, Rina Okada

Proceedings of the IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, 2025

2024

SETSUBUN: Revisiting Membership Inference Game for Evaluating Synthetic Data Generation.

Takayuki Miura, Masanobu Kii, Toshiki Shibahara, Kazuki Iwahana, Tetsuya Okuda, Atsunori Ichikawa, Naoto Yanai

J. Inf. Process., 2024

2023

A Study on Quantized Parameters for Protection of a Model and Its Inference Input.

Hiromasa Kitai, Naoto Yanai, Kazuki Iwahana, Masataka Tatsumi, Jason Paul Cruz

J. Inf. Process., 2023

Sandbox AI: We Don't Trust Each Other but Want to Create New Value Efficiently Through Collaboration Using Sensitive Data.

Osamu Saisho, Keiichiro Kashiwagi, Sakiko Kawai, Kazuki Iwahana, Koki Mitani

Proceedings of the Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing, 2023

Backdoor Attacks Leveraging Latent Representation in Competitive Learning.

Kazuki Iwahana, Naoto Yanai, Toru Fujiwara

Proceedings of the Computer Security. ESORICS 2023 International Workshops, 2023

Can Inputs' Reconstruction Information Be Coded into Machine Learning Model's Outputs?

Kazuki Iwahana, Osamu Saisho, Takayuki Miura, Akira Ito

Proceedings of the Computer Security. ESORICS 2023 International Workshops, 2023

2022

SPGC: Integration of Secure Multiparty Computation and Differential Privacy for Gradient Computation on Collaborative Learning.

Kazuki Iwahana, Naoto Yanai, Jason Paul Cruz, Toru Fujiwara

J. Inf. Process., 2022

MOTUS: How Quantized Parameters Improve Protection of Model and Its Inference Input.

Hiromasa Kitai, Naoto Yanai, Kazuki Iwahana, Masataka Tatsumi, Jason Paul Cruz

Proceedings of the Innovative Security Solutions for Information Technology and Communications, 2022

2021

First to Possess His Statistics: Data-Free Model Extraction Attack on Tabular Data.

Masataka Tasumi, Kazuki Iwahana, Naoto Yanai, Katsunari Shishido, Toshiya Shimizu, Yuji Higuchi, Ikuya Morikawa, Jun Yajima

CoRR, 2021

MADMAX: Browser-Based Malicious Domain Detection Through Extreme Learning Machine.

Kazuki Iwahana, Tatsuya Takemura, Ju Chien Cheng, Nami Ashizawa, Naoki Umeda, Kodai Sato, Ryota Kawakami, Rei Shimizu, Yuichiro Chinen, Naoto Yanai

IEEE Access, 2021

SPGC: An Integrated Framework of Secure Computation and Differential Privacy for Collaborative Learning.

Kazuki Iwahana, Naoto Yanai, Jason Paul Cruz, Toru Fujiwara

Proceedings of the Data Privacy Management, Cryptocurrencies and Blockchain Technology, 2021