PAPERS

2025年の研究業績

2025年（令和7年）の研究業績

学術論文

Mare Hirose, Shoko IMAIZUMI, Hitoshi KIYA,
"Learnable Image Encryption Without Key Management for Privacy-Preserving Vision Transformer",
IEEE Access, Vol. 13, pp. 201351-201362, 2025-11-20. [DOI] [webpage] [Publish] [Local]

国際学会論文

Homare SUEYOSHI, Kiyoshi NISHIKAWA, Hitoshi KIYA,
"A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique",
IEEE Global Conference on Consumer Electronics, グランキューブ大阪（大阪府立国際会議場）, 2025-09-25.
Haruto NAMBA, Sayaka SHIOTA,
"Dual-Feature Ensemble Deep Learning Architecture for Robust Spoofing Speech Detection",
IEEE Global Conference on Consumer Electronics, グランキューブ大阪（大阪府立国際会議場）, 2025-09-25. [Local]
Haiwei Lin , Shoko IMAIZUMI, Hitoshi KIYA,
"Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification",
IEEE Global Conference on Consumer Electronics, グランキューブ大阪（大阪府立国際会議場）, 2025-09-25.
Takuo YAMAGUCHI, Sayaka SHIOTA, Naohiro TAWARA,
"Investigating Self-supervised Learning-Based Front-End for Multi-Channel Replay Attack Detection",
APSIPA Annual Summit and Conference, Shangri-la, Singapore, 2025-10-24. [Local]
Sayaka SHIOTA, Suzuka HORIE, Kota KANNO, Shinnosuke Takamichi,
"J-SPAW: Japanese speaker verification and spoofing attacks recorded in-the-wild dataset",
ISCA International Conference on Interspeech, pp. 3913-3917, ロッテルダム, 2025-08-20. [webpage]
Shinji YAMASHITA, Yuma KINOSHITA, Hitoshi KIYA,
"Scale and Rotation Estimation of Similarity-Transformed Images via Cross-Correlation Maximization Based on Auxiliary Function Method",
APSIPA Annual Summit and Conference, Shangri-la, Singapore, 2025-10-23. [webpage] [Publish] [Local]
Haruya TOMINAGA, Sayaka SHIOTA,
"Speech Privacy-Preserving Method Using Random Permutation of Speech Segments",
IEEE Global Conference on Consumer Electronics, グランキューブ大阪（大阪府立国際会議場）, 2025-09-25. [Local]
Kohei TANAKA, Hitoshi KIYA, Sayaka SHIOTA,
"Voice Privacy Preservation with Multiple Random Orthogonal Secret Keys: Attack Resistance Analysis",
APSIPA Annual Summit and Conference, Shangri-la, Singapore, 2025-10-24. [Local]

学会講演論文

Sawato Furubayashi, Shinnosuke Takamichi, Sayaka SHIOTA,
" A study of speech synthesis attack methods against spoofed speech detection systems.",
General Conference of IEICE, 東京都市大学　世田谷キャンパス, 2025-03-26. [Local]
Koki HORIO, Kiyoshi NISHIKAWA, Hitoshi KIYA,
"A method for enhancing privacy-preserving Vision Transformer using restricted random permutation matrices",
Technical Report of IEICE, Vol. 124, No. 338, pp. EMM2024-105 , 宮城県仙台市青葉区, 2025-01-21. [DOI] [webpage] [Publish] [Local]
Homare SUEYOSHI, Kiyoshi NISHIKAWA, Hitoshi KIYA,
"A privacy-aware object detection method for ViT-based models",
IEICE Signal Processing Symposium, ホテルレイクビュー水戸, 2025-11-26. [Local]
Mare Hirose, Shoko IMAIZUMI, Hitoshi KIYA,
"A privacy-preserving image classification method applicable to multiple clients without key management ",
Technical Report of IEICE, Vol. 124, No. 414, pp. EMM2024-118, 沖縄県青年会館, 2025-03-05. [webpage]
Homare SUEYOSHI, Koki HORIO, Kiyoshi NISHIKAWA, Hitoshi KIYA,
"A privacy-preserving semantic segmentation method that enables model training on cloud servers",
Technical Report of IEICE, Vol. 125, No. 38, pp. EMM2025-7, 長崎大学文教キャンパス, 2025-05-29. [webpage] [Local]
Takuo YAMAGUCHI, Naohiro TAWARA, Hiroshi SATO, Sayaka SHIOTA,
"A verification of combining DNN-based speech enhancement front-end with end-to-end neural dialization model",
Acoustical Society of Japan Spring Meeting, pp. 1083-1084, 埼玉大学, 2025-03-19. [Local]
Hiroto SAWADA, Shoko IMAIZUMI, Hitoshi KIYA,
"An Extension of Privacy-Preserving FedSGD Federated Learning with Random Binary Weights to FedAvg Federated Learning",
Technical Report of IEICE, Vol. 124 , No. 390, pp. SIP2024-151, 沖縄県青年会館, 2025-03-03. [webpage]
Sawato Furubayashi, Shinnosuke Takamichi, Sayaka SHIOTA,
"Attacks Based on Speaker Adaptation-Based Speech Synthesis Against Spoofing Speech Detection Systems.",
Acoustical Society of Japan Autumn Meeting, 東北工業大学八木山キャンパス, 2025-09-12. [Local]
Haiwei Lin , Shoko IMAIZUMI, Hitoshi KIYA,
"Compressible Encryption–Based Privacy-Preserving Action Recognition Using Video Transformer",
IEICE Signal Processing Symposium, ホテルレイクビュー水戸, 2025-11-27. [Local]
Kohei TANAKA, Sayaka SHIOTA,
"Ensemble of Speaker Embeddings in Attentive Pooling-Based Speaker Verification",
Acoustical Society of Japan Autumn Meeting, 東北工業大学八木山キャンパス, 2025-09-12. [Local]
Suzuka HORIE, Shinnosuke Takamichi, Sayaka SHIOTA,
"Impact of recording conditions in replay attacks on spoofed speech detection",
Acoustical Society of Japan Autumn Meeting, 東北工業大学八木山キャンパス, 2025-09-12. [Local]
Suzuka HORIE, Sayaka SHIOTA,
"Impact of recording conditions of recording and playback attacks on spoofed voice detection",
General Conference of IEICE, 東京都市大学　世田谷キャンパス, 2025-03-26. [Local]
Hengyi ZOU, Sayaka SHIOTA,
"Investigating Feature Characteristics of Pseudo-Speaker Data for Speaker Verification",
Acoustical Society of Japan Autumn Meeting, 東北工業大学八木山キャンパス, 2025-09-12. [Local]
Haruya TOMINAGA, Sayaka SHIOTA,
"Speech Privacy-Preserving Methods Using Randomized Reordering of Speech Segments",
General Conference of IEICE, 東京都市大学　世田谷キャンパス, 2025-03-26. [Local]
Haruto NAMBA, Sayaka SHIOTA,
"Speech spoofing detection using deep learning model with multiple acoustic features",
Speech Committee, Vol. 124, No. 391, pp. SP2024-71, 沖縄県青年会館, 2025-03-04. [webpage]
Kota KANNO, Sayaka SHIOTA,
"Verification of Spoofed Speech Detection with Multi-task Learning under Replay Attack Environments",
Acoustical Society of Japan Autumn Meeting, 東北工業大学八木山キャンパス, 2025-09-12. [Local]
Takuo YAMAGUCHI, Naohiro TAWARA, Sayaka SHIOTA,
"マルチチャネルなりすまし音声検出における自己教師あり学習フロントエンドの有効性検証",
IPSJ Music and computer Symposium, Vol. 2025-SLP-156, No. 64, pp. 1-6, 早稲田大学西早稲田キャンパス, 2025-06-14. [webpage] [Local]
Kohei TANAKA, Hitoshi KIYA, Sayaka SHIOTA,
"複数のランダム直交行列に基づく秘密鍵による音声プライバシー保護法の適用要件緩和と攻撃耐性評価",
IPSJ Music and computer Symposium, Vol. 2025-SLP-156, No. 60, pp. 1-6, 早稲田大学西早稲田キャンパス, 2025-06-14. [webpage] [Publish] [Local]