請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81661完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 郭斯彥(Sy-Yen Kuo) | |
| dc.contributor.author | Jhih-Cing Huang | en |
| dc.contributor.author | 黃芷晴 | zh_TW |
| dc.date.accessioned | 2022-11-24T09:25:26Z | - |
| dc.date.available | 2022-11-24T09:25:26Z | - |
| dc.date.copyright | 2021-08-06 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-07-29 | |
| dc.identifier.citation | [1] Edward Farhi and Hartmut Neven. Classification with quantum neural networks on near term processors. arXiv:1802.06002, 2018. [2] https://ai.googleblog.com/2019/10/quantum-supremacy-using-programmable.html [3] Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Dacheng Tao, Nana Liu. Quantum noise protects quantum classifiers against adversaries. Physical Review Research 3, 023153, 2021. [4] I. Cong, S. Choi, and M. D. Lukin, Nature Physics 15, 12731278, 2019. [5] Marcello Benedetti, Delfina Garcia-Pintos, Oscar Perdomo, Vicente Leyton Ortega, Yunseong Nam, and Alejandro PerdomoOrtiz. A generative modeling approach for benchmarking and training shallow quantum circuits. npj Quantum Information, 5(1):1–9, 2019. [6] Pierre-Luc Dallaire-Demers and Nathan Killoran. Quantum generative adversarial networks. Physical Review A, 98(1):012324, 2018. [7] Vojtech Havli cek, Antonio D Corcoles, Kristan Temme, Aram W Harrow, Abhinav Kandala, Jerry M Chow, and Jay M Gambetta. Supervised learning with quantum enhanced feature spaces. Nature, 567(7747):209, 2019. [8] William Huggins, Piyush Patil, Bradley Mitchell, K Birgitta Whaley, and Miles Stoudenmire. Towards quantum machine learning with tensor networks. Quantum Science and Technology, 4(2):024001, 2019. [9] Maria Schuld, Alex Bocharov, Krysta Svore, and Nathan Wiebe. 28 Circuit-centric quantum classifiers. Phys. Rev. A 101, 032308 (2020b). [10] C. Dwork, F. McSherry, K. Nissim, and A. Smith. Calibrating noise to sensitivity in private data analysis. In Theory of Cryptography Conference ’06, pages 265–284. Springer, 2006. [11] Weiyuan Gong, Dong-Ling Deng. Universal Adversarial Examples and Perturbations for Quantum Classifiers. arXiv:2102.07788, 2021. [12] Jeremy M Cohen, Elan Rosenfeld, J. Zico Kolter. Certified Adversarial Robustness via Randomized Smoothing. International Conference on Machine Learning, pages 1310–1320, 2019. [13] Sirui Lu, Lu-Ming Duan, Dong-Ling Deng. Quantum Adversarial Machine Learning. Phys. Rev. Research 2, 033212 (2020). [14] V. Havlicek, A. D. Co ́rcoles, K. Temme, A. W. Harrow, A. Kandala, J. M. Chow, and J. M. Gambetta, Supervised learning with quantum enhanced feature spaces, Nature, 567 209–212 , 2019. [15] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. In International Conference on Learning Representations, 2015. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81661 | - |
| dc.description.abstract | 量子機器學習目前已成為突破機器學習計算速度的潛在可能，其完善化仍是許 多研究團隊的主要目標。現行研究除了設法在量子電腦硬體實作方面進行改善， 針對量子機器學習，傳統機器學習領域的相關研究對應之量子機器學習版本也是 量子計算領域的重點方向。有研究證明量子分類器容易受到機器學習對抗例攻 擊，並且隨著資料的維度增加，其受到對抗例攻擊的風險呈指數增長。本研究利 用外加旋轉雜訊，模擬傳統機器學習隨機平滑演算法，以期達到增加量子分類器 面對對抗例的可靠性，並連結差分隱私之定義，驗證外加雜訊所增強之量子分類 器可耐受對抗例之距離下界。本篇研究探討之量子分類器無特定架構之限制，故 適用於增強所有量子分類器之可靠性。此外，有別於許多傳統機器學習防禦對抗 例之演算法，此量子機器學習演算法不需透過重新訓練量子分類器，即可透過本 研究提出之演算法防禦對抗例。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T09:25:26Z (GMT). No. of bitstreams: 1 U0001-1607202112292200.pdf: 2562248 bytes, checksum: 424fd6e734042fe43919939185714eda (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 1 Introduction 1 2 Related Work 4 2.1 MachineLearning............................. 4 2.2 QuantumMachineLearning ....................... 5 2.3 AdversarialAttack ............................ 6 2.4 CertifiedRobustness ........................... 7 2.5 DifferentialPrivacy............................ 8 3 Preliminary 9 3.1 Notation.................................. 9 3.2 Definition ................................. 10 3.2.1 QuantumClassifier........................ 10 3.2.2 QuantumDifferentialPrivacy .................. 11 4 Proposed Method 13 5 Analysis 15 5.1 AccuracyofNoisyClassifiers....................... 15 5.2 Relation between Noise Magnitude and Quantum Differential Privacy 20 5.3 Connection between Quantum Differential Privacy and Certified Ro- bustness.................................. 21 6 Experiment 24 7 Conclusion 26 8 Reference 28 | |
| dc.language.iso | en | |
| dc.subject | 量子分類器 | zh_TW |
| dc.subject | 差分隱私 | zh_TW |
| dc.subject | 可靠性驗證 | zh_TW |
| dc.subject | 量子雜訊 | zh_TW |
| dc.subject | 量子計算 | zh_TW |
| dc.subject | Quantum Classifier | en |
| dc.subject | Differential Privacy | en |
| dc.subject | Quantum Computation | en |
| dc.subject | Quantum Noise | en |
| dc.subject | Certified Robustness | en |
| dc.title | 利用外加雜訊以增強量子分類器於對抗例之可靠性驗證 | zh_TW |
| dc.title | Certification of Quantum Classifier Robustness against Adversarial Examples through Quantum Noise. | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 游家牧(Hsin-Tsai Liu),陳英一(Chih-Yang Tseng),雷欽隆,顏嗣鈞 | |
| dc.subject.keyword | 差分隱私,可靠性驗證,量子雜訊,量子計算,量子分類器, | zh_TW |
| dc.subject.keyword | Differential Privacy,Quantum Computation,Quantum Noise,Certified Robustness,Quantum Classifier, | en |
| dc.relation.page | 29 | |
| dc.identifier.doi | 10.6342/NTU202101509 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2021-07-30 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1607202112292200.pdf 未授權公開取用 | 2.5 MB | Adobe PDF |
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。