請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87730完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳家麟 | zh_TW |
| dc.contributor.advisor | Ja-Ling Wu | en |
| dc.contributor.author | 潘怡倫 | zh_TW |
| dc.contributor.author | Yi-Lun Pan | en |
| dc.date.accessioned | 2023-07-19T16:09:50Z | - |
| dc.date.available | 2024-02-27 | - |
| dc.date.copyright | 2023-07-19 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-06-07 | - |
| dc.identifier.citation | 1. Y. -L. Pan, J. -C. Chen and J. -L. Wu, "A Multi-Factor Combinations Enhanced Reversible Privacy Protection System for Facial Images," 2021 IEEE International Conference on Multimedia and Expo (ICME), Shenzhen, China, 2021, pp. 1-6, doi: 10.1109/ICME51207.2021.9428264.
2. Ng, H.W.; Winkler, S. A Data-driven Approach to Cleaning Large Face Datasets. In Proceedings of the IEEE international conference on image processing (ICIP), Paris, France, 27–30 October 2014; pp. 343–347. 3. Yi, D.; Lei, Z.; Liao, S.; Li, S.Z. Learning Face Representation from Scratch. arXiv 2014, arXiv:1411.7923. 4. Liu, Z.; Luo, P.; Wang, X.; Tang, X. Deep Learning Face Attributes in the Wild. In Proceedings of the International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015. 5. Deng, J.; Dong, W.; Socher, R.; Li, L.J.; Li, K.; Fei-Fei, L. Imagenet: A Large-scale Hierarchical Image Database. In Proceedings of the 2009 IEEE conference on computer vision and pattern recognition. IEEE, 2009, pp. 248–255. 6. Boyle, M.; Edwards, C.; Greenberg, S. The Effects of Filtered Video on Awareness and Privacy. In Proceedings of the ACM Conference on Computer Supported Cooperative Work, Philadelphia, PA, USA, 2–6 December 2000; pp. 1–10. 7. Neustaedter, C.; Greenberg, S.; Boyle, M. Blur Filtration Fails to Preserve Privacy for Home-Based Video Conferencing. ACM Trans. Comput. Hum. Interact. 2006, 13, 1–36. 8. Phillips, P. Privacy Operating Characteristic for Privacy Protection in Surveillance Applications. In Audio- and Video-Based Biometric Person Authentication; Kanade, T., Jain, A., Ratha, N., Eds.; Lecture Notes in Computer Science; Springer: Berlin/Heidelberg, Germany, 2005; pp. 869–878. 9. Seo, J.; Hwang, S.; Suh, Y.-H. A Reversible Face De-Identification Method based on Robust Hashing. In Proceedings of the International Conference on Consumer Electronics, Algarve, Portugal, 14–16 April 2008. https://doi.org/10.1109/ICCE.2008.4587904. 10. Gross, R.; Sweeney, L.; Cohn, J.; de la Torre, F.; Baker, S. Face De- identification. In Protecting Privacy in Video Surveillance; Senior, A., Ed.; Springer: Berlin/Heidelberg, Germany, 2009. https://doi.org/10.1007/978-1-84882-301-3 8. 11. Newton, E.M.; Sweeney; L.; Malin, B. Preserving privacy by de-identifying face images. IEEE Trans. Knowl. Data Eng. 2005, 17, 232–243. https://doi.org/10.1109/tkde.2005.32. 12. Jourabloo, A.; Yin, X.; Liu, X. Attribute Preserved Face De-identification. In Proceedings of the 2015 International Conference on Biometrics (ICB), Phuket, Thailand, 19–22 May 2015; pp. 278–285. https://doi.org/10.1109/ICB.2015.7139096. 13. Padilla-López, J.R.; Chaaraoui, A.A.; Flórez-Revuelta, F. Visual Privacy Protection Methods: A Survey. Expert Syst. Appl. 2015, 42, 4177–4195. 14. Sweeney, L. k-anonymity: A Model for Protecting Privacy. Int. J. Uncertain. Fuzziness Knowl. -Based Syst. 2002, 10, 557–570. 15. Meden, B.; Žiga Emeršic, Z.; Štruc, V.V.; Peer, P. K-same-net: K-anonymity with Generative Deep Neural Networks for Face Deidentification. Entropy 2018, 20, 60. 16. Pan, Y.-L.; Haung, M.-J.; Ding, K.-T.; Wu, J.-L.; Jang, J.-S.R. K-Same-Siamese-GAN: K-Same Algorithm with Generative Adversarial Network for Facial Image De-identification with Hyperparameter Tuning and Mixed Precision Training. In Proceedings of the 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Taipei, Taiwan, 18–21 September 2019; pp. 1–8. 17. Jeong, Y.; Choi, J.; Kim, S.; Ro, Y.; Oh, T.-H.; Kim, D.; Ha, H.; Yoon, S. FICGAN: Facial Identity Controllable GAN for De-identification. arXiv 2021, arXiv:2110.00740. 18. Yamac, M.; Ahishali, M.; Passalis, N.; Raitoharju, J.; Sankur, B.; Gabbouj, M. Reversible Privacy Preservation using Multi-level Encryption and Compressive Sensing, In Proceedings of the 27th European Signal Processing Conference, A Coruña, Spain, 2–6 September 2019. https://doi.org/10.23919/EUSIPCO.2019.8903056. 19. Gu, X.; Luo, W.; Ryooand, M.; Lee, Y. Password-conditioned Anonymization and Deanonymization with Face Identity Transformers, arXiv 2020, arXiv:1911.11759. https://arxiv.org/abs/1911.11759. 20. Im, D.H.; Seo, Y.S. FaceBERT: Face De-Identification Using VQGAN and BERT. In Proceedings of the 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Republic of Korea, 19–21 October 2022; pp. 2013–2015. https://doi.org/10.1109/ICTC55196.2022.9952883. 21. Yang, J.; Zhang, W.; Liu, J.; Wu, J.; Yang, J. Generating De-identification facial images based on the attention models and adversarial examples. Alex. Eng. J. 2022, 61, 8417–8429. 22. Zhai, L.; Guo, Q.; Xie, X.; Ma, L.; Wang, Y.E.; Liu, Y. A3GAN: Attribute-Aware Anonymization Networks for Face De-identification. In Proceedings of the 30th ACM International Conference on Multimedia (MM '22). Association for Computing Machinery, New York, NY, USA, 10–14 October 2022; pp. 5303–5313. https://doi.org/10.1145/3503161.3547757. 23. Seyyed, K.; Shirin, N. StyleGAN as a Utility-Preserving Face De-identification Method. arXiv 2022, arXiv:2212.02611. 24. Xue, H.; Liu, B.; Yuan, X.; Ding, M.; Zhu, T. Face image de-identification by feature space adversarial perturbation. Concurrency Computat Pract Exper. 2022, 35, e7554. https://doi.org/10.1002/cpe.7554. 25. Bao, J.; Chen, D.; Wen, F.; Li, H.; Hua, G. Towards Open-set Identity Preserving Face Synthesis. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–23 June 2018; pp. 6713–6722. 26. Karras, T.; Laine, S.; Aila, T. A style-based generator architecture for generative adversarial networks. arXiv 2018, arXiv:1812.04948, 2018. 27. Larsen, A.B.L.; Sønderby, S.K.; Larochelle, H.; Winther, O. Autoencoding beyond pixels using a learned similarity metric. arXiv 2015, arXiv:1512.09300. 28. Shen, W.; Liu, R. Learning Residual Images for Face Attribute Manipulation. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 4030–4038. 29. Choi, Y.; Choi, M.; Kim, M.; Ha, J.-W.; Kim, S.; Choo, J. Star- GAN: Unified generative adversarial networks for multi-domain Image- to-Image translation. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 18–22 June 2018; pp. 8789–8797. 30. Lin, J.; Chen, Z.; Xia, Y.; Liu, S.; Qin, T.; Luo, J. Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 43, 1254–1266. 31. Wang, L.; Chen, W.; Yang, W.; Bi, F.; Yu, F. A State-of-the-Art Review on Image Synthesis with Generative Adversarial Networks. Comput. Sci. IEEE Access 2020, 8, 63514–63537. 32. Isola, P.; Zhu, J.-Y.; Zhou, T.; Efros, A. Image-to-image Translation with Conditional Adversarial Networks. In Proceedings of the Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 1125–1134. 33. Finlayson, G.; Hordley, S.; Schaefer, G.; Tian, G.Y. Illuminant and device invariant colour using histogram equalisation. Pattern Recognit. 2005, 38, 179–190. 34. Cao, X.; Wei, Y.; Wen, F.; Sun, J. Face alignment by Explicit Shape Regression. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012; pp. 2887–2894. https://doi.org/10.1109/CVPR.2012.6248015. 35. Rehman, H.Z.U.; Lee, S. Automatic Image Alignment Using Principal Component Analysis. IEEE Access 2018, 6, 72063–72072. https://doi.org/10.1109/ACCESS.2018.2882070. 36. Zhang, K.; Zhang, Z.; Li, Z.; Qiao, Y. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Process. Lett. 2016, 23, 1499–1503. https://doi.org/10.1109/LSP.2016.2603342. 37. Shen, Y.; Zhou, B. Closed-Form Factorization of Latent Semantics in GANs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; pp. 1532–1540. 38. Abadi, M.; Andersen, D.G. Learning to Protect Communications with Adversarial Neural Cryptography, 2016, [arXiv:cs.CR/1610.06918]. 39. Zhu, J.; Kaplan, R.; Johnson, J.; Fei-Fei, L. HiDDeN: Hiding Data With Deep Networks. In Proceedings of the ECCV, 2018. 40. Zhang, K.A.; Cuesta-Infante, A.; Xu, L.; Veeramachaneni, K. SteganoGAN: High Capacity Image Steganography with GANs, 2019,[arXiv:cs.CV/1901.03892]. 41. Tancik, M.; Mildenhall, B.; Ng, R. StegaStamp: Invisible Hyperlinks in Physical Photographs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 42. Hu, D.; Wang, L.; Jiang, W.; Zheng, S.; Li, B. A Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks. IEEE Access 2018, 6, 38303–38314. https://doi.org/10.1109/ACCESS.2018.2852771. 43. Liu, M.m.; Zhang, M.q.; Liu, J.; Zhang, Y.n.; Ke, Y. Coverless Information Hiding Based on Generative adversarial networks, 2017, [arXiv:cs.CR/1712.06951]. 44. Fridrich, J. Steganography in Digital Media: Principles, Algorithms, and Applications; Cambridge University Press, 2009. https://doi.org/10.1017/CBO9781139192903. 45. Li, B.; He, J.; Huang, J.; Shi, Y.Q. A Survey on Image Steganography and Steganalysis. J. Inf. Hiding Multim. Signal Process. 2011,2, 142–172. 46. Baluja, S. Hiding Images in Plain Sight: Deep Steganography. In Proceedings of the Advances in Neural Information Processing Systems;Guyon, I.; Luxburg, U.V.; Bengio, S.; Wallach, H.; Fergus, R.; Vishwanathan, S.; Garnett, R., Eds. Curran Associates, Inc., 2017, Vol. 30. 47. Rehman, A.u.; Rahim, R.; Nadeem, M.S.; Hussain, S.u. End-to-End Trained CNN Encoder-Decoder Networks for Image Steganography. In Proceedings of the Computer Vision - ECCV 2018 Workshops - Munich, Germany, September 8-14, 2018, Proceedings, Part IV; Leal-Taixé, L.;0001, S.R., Eds. Springer, 2018, Vol. 11132, Lecture Notes in Computer Science, pp. 723–729. https://doi.org/10.1007/978-3-030-11018-5_64. 48. Dong, S.; Zhang, R.; Liu, J. Invisible Steganography via Generative Adversarial Network. ArXiv 2018, abs/1807.08571. 49. Fu, Z.; Wang, F.; Xu, C. The Secure Steganography for Hiding Images via GAN. EURASIP Journal on Image and Video Processing 2020, 2020. 50. Tang, W.; Li, B.; Tan, S.; Barni, M.; Huang, J. CNN-Based Adversarial Embedding for Image Steganography. IEEE Transactions on Information Forensics and Security 2019, 14, 2074–2087. https://doi.org/10.1109/TIFS.2019.2891237. 51. Lu, S.P.; Wang, R.; Zhong, T.; Rosin, P.L. Large-capacity Image Steganography Based on Invertible Neural Networks. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021, pp. 10811–10820. 52. Pan YL, Wu JL. Rate-Distortion-Based Stego: A Large-Capacity Secure Steganography Scheme for Hiding Digital Images. Entropy (Basel). 2022 Jul 15;24(7):982. doi: 10.3390/e24070982. PMID: 35885204; PMCID: PMC9318648. 53. Barber, D.; Agakov, F.V. The IM Algorithm: A Variational Approach to Information Maximization. In Proceedings of the NIPS, 2003, pp. 201–208. 54. Cheng, P.; Hao, W.; Dai, S.; Liu, J.; Gan, Z.; Carin, L. CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020) Will be Held in Vienna, Virtual, 12–18 July 2020; pp. 1779–1788. 55. Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. 56. Omkar M. Parkhi, Andrea Vedaldi and Andrew Zisserman. Deep Face Recognition. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 41.1-41.12. BMVA Press, September 2015. 57. M. Maximov, I. Elezi, and L. Leal-Taixe, “Ciagan, “Conditional identity anonymization generative adversarial networks,” in Computer Vision and Pattern Recognition (CVPR). 2020, pp. 5447–5456, IEEE. 58. Prashnani, E.; Cai, H.; Mostofi, Y.; Sen, P. PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. 59. Boehm, B. StegExpose - A Tool for Detecting LSB Steganography, 2014, [arXiv:cs.MM/1410.6656]. 60. Hukkelås, H., Mester, R., Lindseth, F. (2019). DeepPrivacy: A Generative Adversarial Network for Face Anonymization. In Advances in Visual Computing (ISVC 2019). Lecture Notes in Computer Science, vol 11844. Springer, Cham. https://doi.org/10.1007/978-3-030-33720-9_44. 61. Duan, X.; Jia, K.; Li, B.; Guo, D.; Zhang, E.; Qin, C. Reversible Image Steganography Scheme Based on a U-Net Structure. IEEE Access 2019, 7, 9314–9323. https://doi.org/10.1109/ACCESS.2019.2891247. 62. Zhang, K.; Zhang, Z.; Li, Z.; Qiao, Y. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Process. Lett. 2016, 23, 1499–1503. https://doi.org/10.1109/LSP.2016.2603342. 63. Choi, Y.; Uh, J.; Ha, J. Stargan v2: Diverse image synthesis for multiple domains. In Proceedings of the The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020; pp. 8188–8197. 64. Y. Shen, J. Gu, X. Tang, and B. Zhou. Interpreting the latent space of gans for semantic face editing. CVPR 2020. 65. E. Hark onen, A. Hertzmann, J. Lehtinen, and S. Paris. Ganspace: Discovering interpretable gan controls. NeurIPS 2020. 66. https://pypi.org/project/thop/ | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87730 | - |
| dc.description.abstract | 本研究主要因應近年由於消費型鏡頭與計算硬體的蓬勃發展與進步，使得擷取與儲存大量影像資料資料變得非常容易。設想一個資料擁有者，如醫院或是政府機構，是很容易針對個人進行資訊蒐集、儲存與處理。在這樣的情況下，要如何確保資料擁有者可以精準的將每份可識別個人身份 (Identify) 的資料做到保護與個人資料隱藏 (Information Hiding)以達到隱私保護 (Privacy Protection) 的目的；同時，在針對個人資訊完成去識別化與資訊隱藏後，仍能保留相當程度之資料堪用性以利後續特定目的之運用成為機敏資料分析與處理領域的核心研究課題。所以本研究提出了Multi-Task Generative Adversarial Network : Multi-Task GAN網路架構，透過對偶推論 (Dual Inference) 與Rate-Distortion理論，來設計Multi-Task GAN幾項校正損失函數。本研究也提出了對偶Multi-Task GAN網路架構設計完整的物理意義來進行相關理論分析，並搭配多種的實驗來驗證所宣稱的效果。 | zh_TW |
| dc.description.abstract | This study aims to address the ease of capturing and storing large amounts of image data due to the flourishing development and progress of consumer-grade lenses and computing hardware in recent years. As a result, for data owners such as hospitals or government agencies, it has become easy to collect, store, and process personal information. In this context, how to ensure that data owners can accurately protect and hide personally identifiable information (Identity) to achieve privacy protection and information hiding while still retaining a reasonable level of data utility for sensitive data analysis and processing has become a core research issue in the field of sensitive data analysis and processing. Therefore, this study proposes a Multi-Task Generative Adversarial Network (Multi-Task GAN) network architecture, which uses dual inference and rate-distortion theory to correct several loss functions of Multi-Task GAN. The study also presents a complete physical meaning to conduct a theoretical analysis of our system(such as Mutual Information) and validates the claimed effects with relevant experiments. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-07-19T16:09:50Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-07-19T16:09:50Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 ii ABSTRACT iii List of Figures vi List of Tables ix Chapter 1. Introduction 1 Chapter 2. Literature Survey and Benchmark Works 6 2.1 Anonymization and Deanonymization 6 2.2 The Face Generation via Neural Networks 9 2.3 Steganography based on GANs 12 Chapter 3. Neural Network-based Solutions 16 3.1 Scenarios 16 3.2 Multi-Task GAN Model Architecture 18 3.3 The Evolution of our Network Architectures and Related Studies 23 3.4 Flexible Loss Functions Module 25 3.4.1 MfM Loss Functions for Anonymization and De-anonymization 25 3.4.2 SDN Loss Functions for Anonymization and De-anonymization 28 3.4.3 RD-Stego Loss Functions for Steganography 32 Chapter 4. Specific Contributions of the Dissertation 38 4.1 Integration with the Dual Inference Mechanism 38 4.2 Latent Space Manipulations 42 4.2.1 Latent Space Manipulation Analysis of MfM 43 4.2.2 Latent Space Manipulation Analysis of SDN 49 4.3 Information-theoretic-based Cost Functions 55 4.3.1 MfM for Anonymization and De-anonymization 55 4.3.2 SDN for Anonymization and De-anonymization 59 4.3.3 RD-Stego for Information Hiding - Steganography 62 Chapter 5. Materials Used in Experiments and Benchmarking Techniques 67 5.1 Environments for Experiments and Datasets Utilized for Testing 67 5.2 Evaluation Metrics 67 5.3 The Comparable Evaluation Techniques 69 Chapter 6. Experiment Results 71 6.1 MfM for Privacy Protection – Anonymization and De-anonymization 71 6.2 SDN for Privacy Protection – Anonymization and De-anonymization 81 6.3 RD-Stego for Information Hiding - Steganography 88 Chapter 7. Conclusions & Future Works 102 References 104 Appendix – Ablation Study 109 A. SDN for Anonymization and De-anonymization 109 B. RD-Stego for Steganography 112 | - |
| dc.language.iso | en | - |
| dc.title | 人臉影像隱私保護之多任務生成對抗網路設計 | zh_TW |
| dc.title | Multi-Task Generative Adversarial Network Design for Privacy Protection of Facial Images | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 博士 | - |
| dc.contributor.oralexamcommittee | 許超雲;謝邦昌;陳文進;張智星;陳駿丞 | zh_TW |
| dc.contributor.oralexamcommittee | Chau-Yun Hsu;Ben-Chang Shia;Wen-Chin Chen;Jyh-Shing Jang;Jun-Cheng Chen | en |
| dc.subject.keyword | 隱私保護,資料隱藏,對抗式生成網路,對偶推論,率失真理論,匿名性(去識別化),去匿名性(還原識別),相互資訊, | zh_TW |
| dc.subject.keyword | Privacy Protection,Information Hiding,Generative Adversarial Network,Dual Inference,Rate-distortion Theory,Anonymization (De-identification),De-anonymization (Re-identification),Mutual Information, | en |
| dc.relation.page | 116 | - |
| dc.identifier.doi | 10.6342/NTU202300957 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2023-06-08 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf | 48.86 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。