| ［1］Krger J L, Lutz O H M, Raschke P. Privacy implications of voice and speech analysisinformation disclosure by inference［C］ Proc of the 14th IFIP Int Summer School on Privacy and Identity Management (Privacy and Identity). Berlin: Springer, 2019: 242258［2］Yoshioka T, Ragni A, Gales M J F. Investigation of unsupervised adaptation of DNN acoustic models with filter bank input［C］ Proc of IEEE Int Conf on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2014: 63446348［3］Fredrikson M, Lantz E, Jha S, et al. Privacy in pharma cogenetics: An endtoend case study of personalized warfarin dosing［C］ Proc of the 23rd USENIX Security Symp. Berkeley, CA: USENIX Association, 2014: 1732［4］Fredrikson M, Jha S, Ristenpart T. Model inversion attacks that exploit confidence information and basic countermeasures［C］ Proc of the 22nd ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2015: 13221333［5］Zhang Y, Jia R, Pei H, et al. The secret revealer: Generative modelinversion attacks against deep neural networks［C］ Proc of the IEEECVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 253261［6］Chen S, Kahla M, Jia R, et al. Knowledgeenriched distributional model inversion attacks［C］ Proc of the IEEECVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 1617816187［7］Dosovitskiy A, Brox T. Generating images with perceptual similarity metrics based on deep networks［J］. arXiv preprint, arXiv:1602.02644, 2016［8］Jacobsen J H, Smeulders A, Oyallon E. iRevNet: Deep invertible networks［J］. arXiv preprint, arXiv:1802.07088, 2018［9］Gomez A N, Ren M, Urtasun R, et al. The reversible residual network: Backpropagation without storing activations［COL］ Proc of the 31st Conf on Neural Information Processing Systems. 2017［20231013］. https:www.doc88.comp91161589770769.html［10］Yang Z, Zhang J, Chang E C, et al. Neural network inversion in adversarial setting via background knowledge alignment［C］ Proc of the 2019 ACM SIGSAC Conf on Computer Communications Security. New York: ACM, 2019: 225240［11］Dong X, Yin H, Alvarez J M, et al. Deep neural networks are surprisingly reversible: A baseline for zeroshot inversion［J］. arXiv preprint, arXiv: 2107.06304, 2021［12］Wang Z, Song M, Zhang Z, et al. Beyond inferring class representatives: Userlevel privacy leakage from federated learning［C］ Proc of IEEE Conf on Computer and Communications. Piscataway, NJ: IEEE, 2019: 25122520［13］Shi Y, Sagduyu Y, Grushin A. How to steal a machine learning classifier with deep learning［C］ Proc of IEEE Int Symp on Technologies for Homeland Security (HST). Piscataway, NJ: IEEE, 2017: 15［14］Shi Y, Zeng H, Nguyen T T. Adversarial machine learning for network security［C］ Proc of IEEE Int Symp on Technologies for Homeland Security (HST). Piscataway, NJ: IEEE, 2019: 17［15］Zhang Y, Lv Z, Wu H, et al. Mfaconformer: Multiscale feature aggregation conformer for automatic speaker verification［J］. arXiv preprint, arXiv:2203.15249, 2022［16］Desplanques B, Thienpondt J, Demuynck K. ECAPATDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification［J］. arXiv preprint, arXiv:2005.07143, 2020［17］Snyder D, GarciaRomero D, Sell G, et al. Xvectors: Robust DNN embeddings for speaker recognition［C］ Proc of IEEE Int Conf on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2018: 53295333［18］Bu H, Du J, Na X, et al. Aishell1: An opensource mandarin speech corpus and a speech recognition baseline［C］ Proc of the 20th Conf of Oriental Chapter of the Int Coordinating Committee on Speech Databases and Speech IO Systems and Assessment (OCOCOSDA). Piscataway, NJ: IEEE, 2017: 15［19］Waibel A, Hanazawa T, Hinton G, et al. Phoneme recognition using timedelay neural networks［J］. IEEE Trans on Acoustics, Speech, and Signal Processing, 1989, 37(3): 328339 |
