學術產出-學位論文
| 題名 | 在半導體製造中推進數據隱私保護:對 CycleGAN 處理的晶圓圖進行縮略圖保留加密 Advancing Data Privacy in Semiconductor Manufacturing: Thumbnail Preserving Encryption for CycleGAN-Processed Wafer Images |
| 作者 | 黃浚綾 Huang, Chun-Lin |
| 貢獻者 | 曾一凡 Tseng, Yi-Fan 黃浚綾 Huang, Chun-Lin |
| 關鍵詞 | 縮略圖保留加密 CycleGAN CycleGAN Thumbnail preserving encryption |
| 日期 | 2024 |
| 上傳時間 | 5-八月-2024 12:46:38 (UTC+8) |
| 摘要 | 鑒於實際生產線上相對較缺乏有缺陷的晶圓圖，其收集面臨時間限制的挑戰。為了解決晶圓圖中缺陷模式的資料不平衡問題，我們使用 CycleGAN 深度學習網路來開發一個缺陷模式生成解決方案。由於存在硬體設備損壞的風險，我們將生成的晶圓圖存儲在雲端，並以一種 類似縮略圖保留加密的方案，使密文呈現明文的低解析度本，在隱私和安全性之間取得平衡。這個方法旨在提供使用者可用性，同時透過增加缺陷模式的訓練樣本數來促進自動化生產效率。獲得的結果表明，生成的有缺陷晶圓圖與真實的有缺陷晶圓圖非常相似，並且我們計算生成的有缺陷晶圓圖在不同的縮略圖保留加密方案下的峰值訊噪比，以評估其安全性。實驗結果顯示，生成的晶圓圖在R-LSB方案中具有較低的峰值訊噪比及較高的安全性。 Given the limited availability of defective wafer images on actual production lines, there are challenges associated with time constraints in their collection. To address the data imbalance issue concerning defect modes in wafer images, we utilize CycleGAN deep learning networks to devise a defect mode generation solution. Due to the risk of hardware damage, we store the generated wafer images in the cloud and employ an scheme similar to thumbnail preserving encryption to achieve a balance between privacy and security by presenting ciphertext in a low-resolution version of plaintext. This approach aims to provide user accessibility while enhancing automated production efficiency through an increased number of training samples for defect modes. The obtained results indicate a high resemblance between the generated defective wafer images and authentic defective wafer images. Furthermore, we compute the Peak Signal-to-Noise Ratio of the generated defective wafer images under various TPE schemes to assess their security. Experimental results demonstrate that the generated wafer images exhibit lower PSNR values and higher security under the R-LSB scheme. |
| 參考文獻 | [1] Muzhir Shaban Al-Ani and Fouad Hammadi Awad. The jpeg image compression algorithm. Int. J. Adv. Eng. Technol, 6(3):1055–1062, 2013. [2] Aziz Alotaibi.Deep generative adversarial networks for image-to-image translation: A review. Symmetry, 12(10):1705, 2020. [3] Hao-Wen Dong and Yi-Hsuan Yang. Towards a deeper understanding of adversarial losses. arXiv preprint arXiv:1901.08753, 2019. [4] Alberto Fernández, Salvador García, Mikel Galar, Ronaldo C Prati, Bartosz Krawczyk, Francisco Herrera, Alberto Fernández, Salvador García, Mikel Galar, Ronaldo C Prati, et al. Data level preprocessing methods. Learning from Imbalanced Data Sets, pages 79–121, 2018. [5] Ronald Aylmer Fisher and Frank Yates.Statistical tables for biological,agricultural and medical research. Hafner Publishing Company, 1953. [6] Oded Hecht and Giora Dishon. Automatic optical inspection (aoi). In 40th Conference proceedings on electronic components and technology, pages 659–661. IEEE, 1990. [7] Alain Hore and Djemel Ziou. Image quality metrics: Psnr vs. ssim. In 2010 20th international conference on pattern recognition, pages 2366–2369. IEEE, 2010. [8] R Ratheesh Kumar and Jabin Mathew. Image encryption: Traditional methods vs alternative methods. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), pages 1–7. IEEE, 2020. [9] Xuanqing Liu and Cho-Jui Hsieh. Rob-gan: Generator, discriminator, and adversarial attacker. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11234–11243, 2019. [10] Hans Marmolin. Subjective mse measures. IEEE transactions on systems, man, and cybernetics, 16(3):486–489, 1986. [11] Byron Marohn, Charles V Wright, Wu-chi Feng, Mike Rosulek, and Rakesh B Bobba. Approximate thumbnail preserving encryption. In Proceedings of the 2017 on Multimedia Privacy and Security, pages 33–43. 2017. [12] Chandran Saravanan. Color image to grayscale image conversion. In 2010 Second International Conference on Computer Engineering and Applications, volume 2, pages 196–199. IEEE, 2010. [13] Kimia Tajik, Akshith Gunasekaran, Rhea Dutta, Brandon Ellis, Rakesh B Bobba, Mike Rosulek, Charles V Wright, and Wu-chi Feng. Balancing image privacy and usability with thumbnail-preserving encryption. IACR Cryptol. ePrint Arch., 2019:295, 2019. [14] Du-Ming Tsai, Morris SK Fan, Yi-Quan Huang, and Wei-Yao Chiu. Saw-mark defect detection in heterogeneous solar wafer images using gan-based training samples generation and cnn classification. In VISIGRAPP (5: VISAPP), pages 234–240, 2019. [15] Du-Ming Tsai, Yi-Quan Huang, and Wei-Yao Chiu. Deep learning from imbalanced data for automatic defect detection in multicrystalline solar wafer images. Measurement Science and Technology, 32(12):124003, 2021. [16] Justin Veiner, Fady Alajaji, and Bahman Gharesifard. A unifying generator loss function for generative adversarial networks. Entropy, 26(4):290, 2024. [17] Junliang Wang, Zhengliang Yang, Jie Zhang, Qihua Zhang, and Wei-Ting Kary Chien. Adabalgan: An improved generative adversarial network with imbalanced learning for wafer defective pattern recognition. IEEE Transactions on Semiconductor Manufacturing, 32(3):310–319, 2019. [18] Charles V Wright, Wu-chi Feng, and Feng Liu. Thumbnail-preserving encryption for jpeg. In Proceedings of the 3rd ACM Workshop on Information Hiding and Multimedia Security, pages 141–146, 2015. [19] Ming-Ju Wu, Jyh-Shing R Jang, and Jui-Long Chen. Wafer map failure pattern recognition and similarity ranking for large-scale data sets. IEEE Transactions on Semiconductor Manufacturing, 28(1):1–12, 2014. [20] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017. |
| 描述 | 碩士 國立政治大學 資訊科學系 111753210 |
| 資料來源 | http://thesis.lib.nccu.edu.tw/record/#G0111753210 |
| 資料類型 | thesis |
| dc.contributor.advisor | 曾一凡 | zh_TW |
| dc.contributor.advisor | Tseng, Yi-Fan | en_US |
| dc.contributor.author (作者) | 黃浚綾 | zh_TW |
| dc.contributor.author (作者) | Huang, Chun-Lin | en_US |
| dc.creator (作者) | 黃浚綾 | zh_TW |
| dc.creator (作者) | Huang, Chun-Lin | en_US |
| dc.date (日期) | 2024 | en_US |
| dc.date.accessioned | 5-八月-2024 12:46:38 (UTC+8) | - |
| dc.date.available | 5-八月-2024 12:46:38 (UTC+8) | - |
| dc.date.issued (上傳時間) | 5-八月-2024 12:46:38 (UTC+8) | - |
| dc.identifier (其他 識別碼) | G0111753210 | en_US |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/152576 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 資訊科學系 | zh_TW |
| dc.description (描述) | 111753210 | zh_TW |
| dc.description.abstract (摘要) | 鑒於實際生產線上相對較缺乏有缺陷的晶圓圖，其收集面臨時間限制的挑戰。為了解決晶圓圖中缺陷模式的資料不平衡問題，我們使用 CycleGAN 深度學習網路來開發一個缺陷模式生成解決方案。由於存在硬體設備損壞的風險，我們將生成的晶圓圖存儲在雲端，並以一種 類似縮略圖保留加密的方案，使密文呈現明文的低解析度本，在隱私和安全性之間取得平衡。這個方法旨在提供使用者可用性，同時透過增加缺陷模式的訓練樣本數來促進自動化生產效率。獲得的結果表明，生成的有缺陷晶圓圖與真實的有缺陷晶圓圖非常相似，並且我們計算生成的有缺陷晶圓圖在不同的縮略圖保留加密方案下的峰值訊噪比，以評估其安全性。實驗結果顯示，生成的晶圓圖在R-LSB方案中具有較低的峰值訊噪比及較高的安全性。 | zh_TW |
| dc.description.abstract (摘要) | Given the limited availability of defective wafer images on actual production lines, there are challenges associated with time constraints in their collection. To address the data imbalance issue concerning defect modes in wafer images, we utilize CycleGAN deep learning networks to devise a defect mode generation solution. Due to the risk of hardware damage, we store the generated wafer images in the cloud and employ an scheme similar to thumbnail preserving encryption to achieve a balance between privacy and security by presenting ciphertext in a low-resolution version of plaintext. This approach aims to provide user accessibility while enhancing automated production efficiency through an increased number of training samples for defect modes. The obtained results indicate a high resemblance between the generated defective wafer images and authentic defective wafer images. Furthermore, we compute the Peak Signal-to-Noise Ratio of the generated defective wafer images under various TPE schemes to assess their security. Experimental results demonstrate that the generated wafer images exhibit lower PSNR values and higher security under the R-LSB scheme. | en_US |
| dc.description.tableofcontents | 1. Introduction 1 1.1.Related Works 3 1.2.Contributions 4 2.Preliminaries 5 2.1.CycleGAN Core Architecture 5 2.1.1.Adversarial Loss 5 2.1.2.Cycle Consistency Loss 6 2.1.3.Total Loss Function 6 2.2.Dynamic Range Extension 6 2.3.Dynamic Range Preserving Encryption 7 2.4.Thumbnail Preserving Encryption with LSB Embedding 7 2.5 Hybrid Dynamic Range Preserving Encryption with LSB Embedding 9 2.6 Block Encryption 10 2.7 Recursive Block Encryption 10 2.8 Peak Signal-to-Noise Ratio 11 3.Core Architectural Framework Process 13 3.1.Generation of Defective Wafer Images 13 3.2.Thumbnail Preserving Encryption for Defective Wafer Images 14 4.Comparison 16 4.1.Experimental Result 16 4.2.Analysis of Peak Signal-to-Noise Ratio 17 5. Conclusion 22 Reference 23 | zh_TW |
| dc.format.extent | 1901018 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0111753210 | en_US |
| dc.subject (關鍵詞) | 縮略圖保留加密 | zh_TW |
| dc.subject (關鍵詞) | CycleGAN | zh_TW |
| dc.subject (關鍵詞) | CycleGAN | en_US |
| dc.subject (關鍵詞) | Thumbnail preserving encryption | en_US |
| dc.title (題名) | 在半導體製造中推進數據隱私保護:對 CycleGAN 處理的晶圓圖進行縮略圖保留加密 | zh_TW |
| dc.title (題名) | Advancing Data Privacy in Semiconductor Manufacturing: Thumbnail Preserving Encryption for CycleGAN-Processed Wafer Images | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | [1] Muzhir Shaban Al-Ani and Fouad Hammadi Awad. The jpeg image compression algorithm. Int. J. Adv. Eng. Technol, 6(3):1055–1062, 2013. [2] Aziz Alotaibi.Deep generative adversarial networks for image-to-image translation: A review. Symmetry, 12(10):1705, 2020. [3] Hao-Wen Dong and Yi-Hsuan Yang. Towards a deeper understanding of adversarial losses. arXiv preprint arXiv:1901.08753, 2019. [4] Alberto Fernández, Salvador García, Mikel Galar, Ronaldo C Prati, Bartosz Krawczyk, Francisco Herrera, Alberto Fernández, Salvador García, Mikel Galar, Ronaldo C Prati, et al. Data level preprocessing methods. Learning from Imbalanced Data Sets, pages 79–121, 2018. [5] Ronald Aylmer Fisher and Frank Yates.Statistical tables for biological,agricultural and medical research. Hafner Publishing Company, 1953. [6] Oded Hecht and Giora Dishon. Automatic optical inspection (aoi). In 40th Conference proceedings on electronic components and technology, pages 659–661. IEEE, 1990. [7] Alain Hore and Djemel Ziou. Image quality metrics: Psnr vs. ssim. In 2010 20th international conference on pattern recognition, pages 2366–2369. IEEE, 2010. [8] R Ratheesh Kumar and Jabin Mathew. Image encryption: Traditional methods vs alternative methods. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), pages 1–7. IEEE, 2020. [9] Xuanqing Liu and Cho-Jui Hsieh. Rob-gan: Generator, discriminator, and adversarial attacker. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11234–11243, 2019. [10] Hans Marmolin. Subjective mse measures. IEEE transactions on systems, man, and cybernetics, 16(3):486–489, 1986. [11] Byron Marohn, Charles V Wright, Wu-chi Feng, Mike Rosulek, and Rakesh B Bobba. Approximate thumbnail preserving encryption. In Proceedings of the 2017 on Multimedia Privacy and Security, pages 33–43. 2017. [12] Chandran Saravanan. Color image to grayscale image conversion. In 2010 Second International Conference on Computer Engineering and Applications, volume 2, pages 196–199. IEEE, 2010. [13] Kimia Tajik, Akshith Gunasekaran, Rhea Dutta, Brandon Ellis, Rakesh B Bobba, Mike Rosulek, Charles V Wright, and Wu-chi Feng. Balancing image privacy and usability with thumbnail-preserving encryption. IACR Cryptol. ePrint Arch., 2019:295, 2019. [14] Du-Ming Tsai, Morris SK Fan, Yi-Quan Huang, and Wei-Yao Chiu. Saw-mark defect detection in heterogeneous solar wafer images using gan-based training samples generation and cnn classification. In VISIGRAPP (5: VISAPP), pages 234–240, 2019. [15] Du-Ming Tsai, Yi-Quan Huang, and Wei-Yao Chiu. Deep learning from imbalanced data for automatic defect detection in multicrystalline solar wafer images. Measurement Science and Technology, 32(12):124003, 2021. [16] Justin Veiner, Fady Alajaji, and Bahman Gharesifard. A unifying generator loss function for generative adversarial networks. Entropy, 26(4):290, 2024. [17] Junliang Wang, Zhengliang Yang, Jie Zhang, Qihua Zhang, and Wei-Ting Kary Chien. Adabalgan: An improved generative adversarial network with imbalanced learning for wafer defective pattern recognition. IEEE Transactions on Semiconductor Manufacturing, 32(3):310–319, 2019. [18] Charles V Wright, Wu-chi Feng, and Feng Liu. Thumbnail-preserving encryption for jpeg. In Proceedings of the 3rd ACM Workshop on Information Hiding and Multimedia Security, pages 141–146, 2015. [19] Ming-Ju Wu, Jyh-Shing R Jang, and Jui-Long Chen. Wafer map failure pattern recognition and similarity ranking for large-scale data sets. IEEE Transactions on Semiconductor Manufacturing, 28(1):1–12, 2014. [20] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017. | zh_TW |