簡易檢索 / 詳目顯示

研究生: 謝明諺
MING-YEN HSIEH
論文名稱: 應用大型語言模型於低功耗藍牙通訊中進行滲透測試及弱點辨識
Applying Large Language Models for Penetration Testing and Vulnerability Identification in Bluetooth Low Energy Communication
指導教授: 呂政修
Jenq-Shiou Leu
口試委員: 陳郁堂
Yie-Tarng Chen
方文賢
Wen-Hsien Fang
周承復
Cheng-Fu Chou
學位類別: 碩士
Master
系所名稱: 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年: 2023
畢業學年度: 112
語文別: 中文
論文頁數: 37
中文關鍵詞: 低功耗藍牙漏洞掃描滲透測試機器學習大型語言模型自動化分析資安強化
外文關鍵詞: Bluetooth Low Energy, Vulnerability Scanning, Penetration Testing, Machine Learning, Large Language Models, Automated Analysis, Cybersecurity Enhancement
相關次數: 點閱:63下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報


指導教授推薦書 ................................2 審定書 ..........3 摘要 ..............4 ABSTRACT .............5 圖表索引 ...................9 第 1 章 緒論 ....................................10 1.1 研究背景與動機 ...............10 1.2 研究目的 ...........................13 1.3 章節提要 ...........................14 第 2 章 相關文獻 ............................15 2.1 針對 BLE 的攻擊 .............15 2.1.1 被動竊聽 ....................15 2.1.2 主動竊聽 ....................15 2.1.3 設備複製 ....................15 2.1.4 加密漏洞 ....................16 2.1.5 拒絕服務 ....................16 2.1.6 監視 ............................16 2.2 BLE 通訊過程漏洞檢測相關的技術 .....................17 2.2.1 滲透測試 ....................17 2.2.2 機器學習/深度學習 ..17 2.3 LLM ...................................18 2.3.1 Zero-Shot Prompt ........18 2.3.2 Few-Shot Prompt ........18 2.3.3 Toolformer ..................19 第 3 章 方法設計 ............................20 3.1 漏洞掃描方法比較 ...........20 3.2 Prompt 介紹 .......................21 3.3 資料轉換 ...........................22 3.4 方法流程圖 .......................22 3.5 建立藍牙知識庫 ...............23 3.6 封包分析細節 ...................23 3.7 挑選工具細節 ...................24 3.8 滲透測試細節 ...................24 3.9 整合結果細節 ...................24 第 4 章 實驗結果 ............................25 4.1 實驗設備介紹 ....................25 4.2 實驗工具介紹 ....................27 4.3 實驗設置 ............................27 4.4 實驗結果 ............................29 第 5 章 結論 ....................................30 參考文獻 ...................31 附錄 ............................33 系統展示 ..................................33

[1] J. DeCuir, "Introducing Bluetooth Smart: Part 1: A look at both classic and new technologies," IEEE Consumer Electronics Magazine, vol. 3, no. 1, pp. 12-18, 2013.
[2] B. Farzaneh, M. A. Montazeri, and S. Jamali, "An anomaly-based IDS for detecting attacks in RPL-based internet of things," in 2019 5th International Conference on Web Research (ICWR), 2019: IEEE, pp. 61-66.
[3] J. T. Vainio, "Bluetooth security," in Proceedings of Helsinki University of Technology, Telecommunications Software and Multimedia Laboratory, Seminar on Internetworking: Ad Hoc Networking, Spring, 2000, vol. 5.
[4] A. Barua, M. A. Al Alamin, M. S. Hossain, and E. Hossain, "Security and privacy threats for bluetooth low energy in iot and wearable devices: A comprehensive survey," IEEE Open Journal of the Communications Society, vol. 3, pp. 251-281, 2022.
[5] M. T. Dini and V. Sokolov, "Penetration tests for Bluetooth low energy and Zigbee using the software-defined radio," arXiv preprint arXiv:1902.08595,2019.
[6] M. Yaseen et al., "Marc: A novel framework for detecting mitm attacks in ehealthcare ble systems," Journal of medical systems, vol. 43, pp. 1-18, 2019.
[7] A. Lahmadi, A. Duque, N. Heraief, and J. Francq, "MitM attack detection in BLE networks using reconstruction and classification machine learning techniques," in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2020: Springer, pp. 149-164.
[8] S. Sevier and A. Tekeoglu, "Analyzing the security of Bluetooth low energy," in 2019 International Conference on Electronics, Information, and Communication (ICEIC), 2019: IEEE, pp. 1-5.
[9] S. Pallavi and V. A. Narayanan, "An overview of practical attacks on BLE Based IOT devices and their security," in 2019 5th international conference on advanced computing & communication systems (ICACCS), 2019: IEEE, pp.694-698.
[10] J. Wu et al., "{BLESA}: Spoofing attacks against reconnections in bluetooth low energy," in 14th USENIX Workshop on Offensive Technologies (WOOT 20),2020.
[11] Y. Zhang, J. Weng, R. Dey, Y. Jin, Z. Lin, and X. Fu, "On the (in) security of bluetooth low energy one-way secure connections only mode," arXiv preprint arXiv:1908.10497, 2019.
[12] D. Antonioli, N. O. Tippenhauer, K. Rasmussen, and M. Payer, "BLURtooth: exploiting cross-transport key derivation in bluetooth classic and bluetooth low energy," in Proceedings of the 2022 ACM on Asia conference on computer and communications security, 2022, pp. 196-207.
[13] J. Uher, R. G. Mennecke, and B. S. Farroha, "Denial of Sleep attacks in Bluetooth Low Energy wireless sensor networks," in MILCOM 2016-2016 IEEE Military Communications Conference, 2016: IEEE, pp. 1231-1236.
[14] A. L. Buczak and E. Guven, "A survey of data mining and machine learning methods for cyber security intrusion detection," IEEE Communications surveys & tutorials, vol. 18, no. 2, pp. 1153-1176, 2015.
[15] T. Brown et al., "Language models are few-shot learners," Advances in neural information processing systems, vol. 33, pp. 1877-1901, 2020.
[16] T. Schick et al., "Toolformer: Language models can teach themselves to use tools," arXiv preprint arXiv:2302.04761, 2023.
[17] J. Wei et al., "Chain-of-thought prompting elicits reasoning in large language models," Advances in Neural Information Processing Systems, vol. 35, pp.24824-24837, 2022.

無法下載圖示 全文公開日期 2026/02/01 (校內網路)
全文公開日期 2026/02/01 (校外網路)
全文公開日期 2026/02/01 (國家圖書館:臺灣博碩士論文系統)
QR CODE