PAPERS

Publications in 2024

Journal Papers

Teru NAGAMORI, Sayaka SHIOTA, Hitoshi KIYA,
"Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer",
APSIPA Trans. Signal and Information Processing, Vol. 13, No.1, e8, 2024-04-08. [DOI] [webpage]
Ryota IIJIMA, Sayaka SHIOTA, Hitoshi KIYA,
"A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense",
IEEE Access, Vol. 12, pp. 69206-69216, 2024-05-14. [DOI] [webpage]
Mare Hirose, Shoko IMAIZUMI, Hitoshi KIYA,
"Encryption Method for JPEG Bitstreams for Partially Disclosing Visual Information",
MDPI electronics, Vol. 13, No. 11, 2024-05-22. [DOI]
April Pyone MAUNG MAUNG, Isao ECHIZEN, Hitoshi KIYA,
"Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model",
IEEE Open Journal of Signal Processing, Vol. 5, pp. 902-913, 2024-07-26. [DOI]
April Pyone MAUNG MAUNG, Isao ECHIZEN, Hitoshi KIYA,
"On the Security of Learnable Image Encryption for Privacy-Preserving Deep Learning",
IEEE Access, Vol. 12, pp. 126415-126425, 2024-09-05. [DOI] [webpage]
Shoko NIWA, Sayaka SHIOTA, Hitoshi KIYA,
"Speech Privacy-preserving Methods Using Secret Key for Convolutional Neural Network Models and Their Robustness Evaluation",
APSIPA Trans. Signal and Information Processing, Vol. 13, No. 1, 2024-10-23. [DOI] [webpage]
Haiwei Lin , Shoko IMAIZUMI, Hitoshi KIYA,
"Privacy-Preserving ConvMixer Without Any Accuracy Degradation Using Compressible Encrypted Images",
MDPI Information, Vol. 15, No. 11, p. 723, 2024-11-11. [DOI] [webpage]

International Conference Papers

Ryota IIJIMA, Sayaka SHIOTA, Hitoshi KIYA,
"A Random Ensemble of Encrypted Models for Enhancing Robustness against Adversarial Examples",
RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing, 2024-02-27. [Publish]
April Pyone MAUNG MAUNG, Huy H. Nguyen, Hitoshi KIYA, Isao ECHIZEN,
"FINE-TUNING TEXT-TO-IMAGE DIFFUSION MODELS FOR CLASS-WISE SPURIOUS FEATURE GENERATION",
IEEE International Conference on Image Processing, 2024-10-27. [Publish]
April Pyone MAUNG MAUNG, Huy H. Nguyen, Hitoshi KIYA, Isao ECHIZEN,
"Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation",
IEEE International Conference on Image Processing, pp. 3910-3916, 2024-10-27. [DOI]
Koki HORIO, Kiyoshi NISHIKAWA, Hitoshi KIYA,
"Privacy-Preserving Vision Transformer Using Images Encrypted with Restricted Random Permutation Matrices",
IEEE Global Conference on Consumer Electronics, 2024-10-31.
Hiroto SAWADA, Shoko IMAIZUMI, Hitoshi KIYA,
"Enhancing Security Using Random Binary Weights in Privacy-Preserving Federated Learning",
APSIPA Annual Summit and Conference, 2024-12-05.
Mare Hirose, Shoko IMAIZUMI, Hitoshi KIYA,
"On the Security of Bitstream-level JPEG Encryption with Restart Markers",
APSIPA Annual Summit and Conference, 2024-12-05.
Rei ASO, Sayaka SHIOTA, Hitoshi KIYA,
"Disposable-key-based image encryption for collaborative learning of Vision Transformer",
APSIPA Annual Summit and Conference, 2024-12-05.
Yuma KINOSHITA, Hitoshi KIYA,
"Scene-Segmentation-Based Exposure Compensation for Tone Mapping of High Dynamic Range Scenes",
APSIPA Annual Summit and Conference, 2024-12-05.
Hengyi ZOU, Sayaka SHIOTA,
"Vocal Tract Length Perturbation-based Pseudo-Speaker Augmentation Considering Speaker Variability for Speaker Verification",
APSIPA Annual Summit and Conference, 2024-12-06.

Domestic Conference Papers

Mare Hirose, Shoko IMAIZUMI, Hitoshi KIYA,
"An encryption method of JPEG bitstreams for partially disclosing visual information ",
Technical Report of IEICE, Vol. 123, No. 332, pp. 26-31, 2024-01-17. [webpage]
Shoko NIWA, Sayaka SHIOTA, Hitoshi KIYA,
"Robustness Against Attacks on a Voice Privacy-preserving Method Using Random Orthogonal Matrix-based Secret Key",
IEICE Symposium on Cryptography and Information Security, 2024-01-24.
Rei ASO, Sayaka SHIOTA, Hitoshi KIYA,
"An Enhanced Privacy-Preserving Scheme for Federated Learning of Vision Transformer without Model Performance Degradation ",
Technical Report of IEICE, Vol. 123, No. 402, pp. 115-120, 2024-02-29. [webpage]
Fumika ONO, Tomoka WAKAMATSU, Sayaka SHIOTA,
"Pseudo-speaker augmentation based on vocal tract length perturbation considering speaker variability for speaker verification",
Speech Committee, Vol. 123, No. 403, pp. SP2023-44, 2024-02-29. [webpage] [Publish]
Tomoka WAKAMATSU, Sayaka SHIOTA, Hitoshi KIYA,
"Vocal tract length perturbation-based pseudo-speaker augmentation for automatic speaker verification",
Speech Committee, Vol. 123, No. 403, pp. SP-2023-43, 2024-02-29. [webpage] [Publish]
Eri HIRAYAMA, Sayaka SHIOTA,
"話者照合コーパスJTubeSpeech-ASVにおける言語と性別による影響調査",
General Conference of IEICE, pp. 73-73, 2024-03-07. [Publish]
Sora WATABE, Sayaka SHIOTA,
"話者照合のためのなりすまし音声検出に対するノイズ重畳の影響調査",
General Conference of IEICE, pp. 72-72, 2024-03-07. [Publish]
Hiroto SAWADA, Shoko IMAIZUMI, Hitoshi KIYA,
"Enhanced Security with Random Binary Weights for Privacy-Preserving Federated Learning ",
Technical Report of IEICE, Vol. 124, No. 58, pp. 1, 2024-06-06. [webpage]
Kota KANNO, Shinnosuke Takamichi, Sayaka SHIOTA,
"J-SpAW: Japanese corpus for speaker verification and spoofing attack detection, recorded in the wild",
IPSJ Music and computer Symposium, Vol. 152, No. 52, pp. 1-7, 2024-06-07. [webpage] [Publish]
Koki HORIO, Kiyoshi NISHIKAWA, Hitoshi KIYA,
"A fine-tuning method using encrypted pre-trained model for Vision Transformer considering privacy protection",
Technical Report of IEICE, Vol. 124, No. 112, pp. 21, 2024-07-11. [webpage]
Kohei TANAKA, Hitoshi KIYA, Sayaka SHIOTA,
"Enhancing robustness using multiple random orthogonal matrices for voice privacy-preserving",
Technical Report of IEICE, Vol. 124, No. 162, pp. SIP2024-53, 2024-08-19. [webpage]
Rei ASO, Sayaka SHIOTA, Hitoshi KIYA,
"Disposable key-based image encryption for muti-participant DNN learning",
Technical Report of IEICE, Vol. 124, No. 162, pp. SIP2024-47, 2024-08-26. [webpage]
Yuma KINOSHITA, Hitoshi KIYA,
"Scene-Segmentation-Based Exposure Compensation for Tone Mapping by Multi-Exposure Image Fusion",
IEICE Signal Processing Symposium, 2024-12-18.