簡易檢索 / 詳目顯示

研究生: 楊朝順
Yang, Chao-Shun
論文名稱: 結合簽章與隱寫技術之RGB影像來源驗證機制以抵擋假訊息
An RGB Image Source Verification Mechanism Combining Signatures and Steganography to Combat Misinformation
指導教授: 莊允心
Chuang, Yun-Hsin
學位類別: 碩士
Master
系所名稱: 工學院 - 工程管理碩士在職專班
Engineering Management Graduate Program(on-the-job class)
論文出版年: 2025
畢業學年度: 113
語文別: 中文
論文頁數: 50
中文關鍵詞: 假新聞假圖片數位簽章浮水印隱寫術
外文關鍵詞: Fake News, Fake Images, RSA, Watermarking, Steganography
相關次數: 點閱:4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
  • 社群媒體與行動通訊技術的普及,使得具惡意目的之假新聞與假圖片以前所未有的速度與廣度傳播,對個人認知、社會秩序乃至國家安全構成嚴峻挑戰。此類虛假訊息不僅被用以誤導公眾、操縱輿論,更可能干預選舉、挑起社會衝突,嚴重威脅民主發展與社會安定。傳統上依賴「眼見為憑」的資訊驗證方式,在面對日新月異的影像偽造與人工智慧生成技術時顯得捉襟見肘,亟需更可靠的驗證機制用以確保資訊的真實性。本論文針對上述問題,探討當前網路假訊息的傳播特性與作假手法深入探討影像內容的偽造與辨識困境。為有效應對日益精密的影像偽造技術,本論文提出一種結合數位簽章與隱寫術的影像來源驗證機制,兼顧隱私性與安全性的輕量級影像來源驗證方案,巧妙地結合了隱寫圖片的資訊承載能力與非對稱式密碼系統的簽章驗證機制,以期構建更安全、更可信的網路資訊環境,有效遏制假圖片等虛假資訊的傳播,維護社會的穩定與安全。

    The widespread use of social media and mobile communication technologies has enabled maliciously crafted fake news and fabricated images to disseminate at unprecedented speed and scale, posing serious challenges to individual cognition, social order, and even national security. Such misinformation is not only used to mislead the public and manipulate public opinion but can also interfere with elections and incite social conflict, thereby threatening democratic development and societal stability. Traditional verification methods that rely on “seeing is believing” have become increasingly inadequate in the face of rapidly evolving image forgery techniques and AI-generated content, underscoring the urgent need for more reliable mechanisms to ensure the authenticity of information. In response to these issues, this thesis examines the dissemination characteristics and fabrication techniques of online misinformation and investigates the challenges associated with image forgery and content authentication. To counter the growing sophistication of image manipulation technologies, the thesis proposes an image-source verification mechanism that integrates digital signatures with steganography. The resulting lightweight solution balances privacy and security by leveraging the information-carrying capability of steganographic images together with the signature-verification properties of asymmetric cryptographic systems. The goal is to establish a safer and more trustworthy online information environment, effectively curb the spread of fake images and other forms of disinformation, and uphold social stability and security.

    摘要 III Extended Abstract IV 誌謝 VIII 表目錄 XI 圖目錄 XII 第一章 緒論 1 1.1研究背景 1 1.2 研究動機 4 1.3主要貢獻 7 第二章 預備知識 9 2.1浮水印 (Watermarking) 9 2.2雜湊函數(Hash function) 10 2.3公開鑰匙密碼系統(Public Key Cryptosystem ) 11 2.4常見圖片的檔案種類 13 第三章 文獻探討 16 第四章 影像來源驗證技術 19 4.1基於非對稱式密碼系統之影像來源驗證機制 19 4.2 設計優勢與成果 23 第五章 分析與比較 24 5.1 經典影像實驗 24 5.2 實驗結果分析 28 5.3 LSB圖片比較 31 第六章 結論與未來工作 35 參考文獻 36

    [1] Wardle, Claire. "Fake news. It’s complicated." First draft 16 (2017): 1-11.
    [2] Hsu, Chih-Chung, Yi-Xiu Zhuang, and Chia-Yen Lee. "Deep fake image detection based on pairwise learning." Applied Sciences 10.1 (2020): 370.
    [3] Chen, Xinran, et al. "Why students share misinformation on social media: Motivation, gender, and study-level differences." The journal of academic librarianship 41.5 (2015): 583-592.
    [4] Friedlander, Emilie. “Why People Post Fake News.” Vice, 11 Mar. 2019, https://www.vice.com/en_us/article/9kpz3v/why-people-post-fake-news-v26n1 (accessed May 5, 2025).
    [5] Talwar, Shalini, et al. "Why do people share fake news? Associations between the dark side of social media use and fake news sharing behavior." Journal of retailing and consumer services 51 (2019): 72-82.
    [6] Hartford Courant, “Software startup Truepic aims to stamp out internet fakery,”Hartford Courant, Mar. 20, 2019.https://www.courant.com/2019/03/20/software-startup-truepic-aims-to-stamp-out-internet-fakery/ (accessed May 10, 2025).
    [7] “搞懂四個問題 Deepfake騙不了你的心 | 《全民查假會社》 TSTM,” Tstm.tw, 2023. https://tstm.tw/Article/Detail/5193 (accessed May 12, 2025).
    [8] S. Dunn, “Women, Not Politicians, Are Targeted Most Often by Deepfake Videos,” Centre for International Governance Innovation, Mar. 03, 2021. https://www.cigionline.org/articles/women-not-politicians-are-targeted-most-often-deepfake-videos/(accessed May 15, 2025).
    [9] Thangadurai, K., and G. Sudha Devi. "An analysis of LSB based image steganography techniques." 2014 international conference on computer communication and informatics. IEEE, 2014.
    [10] Cayre, François, Caroline Fontaine, and Teddy Furon. "Watermarking security: theory and practice." IEEE Transactions on signal processing 53.10 (2005): 3976-3987.
    [11] CodingMan, “CodingMan.cc,” CodingMan.cc, Oct. 13, 2024.https://codingman.cc/what-is-hash-function/ (accessed May 16, 2025).
    [12] Ahmed, Fawad, Mohammed Yakoob Siyal, and Vali Uddin Abbas. "A secure and robust hash-based scheme for image authentication." Signal Processing 90.5 (2010): 1456-1470.
    [13] Stamp, Mark. Information security: principles and practice. John Wiley & Sons, 2011.
    [14] William Stallings, Cryptography and network security, 8/E. Pearson FT Press, 2022.
    [15] Wang, Kan, Zhe-Ming Lu, and Yong-Jian Hu. "A high capacity lossless data hiding scheme for JPEG images." Journal of systems and software 86.7 (2013): 1965-1975.
    [16] Lin, Jingzhi, et al. "A new steganography method for dynamic GIF images based on palette sort." Wireless Communications and Mobile Computing 2020.1 (2020): 8812087.
    [17] Zin, Wai Wai. "Message embedding in PNG file using LSB steganographic technique." International Journal of Science and Research 2.1 (2013).
    [18] 林岳. "可逆式浮水印嵌入法則之硬體架構實現之研究." 臺灣師範大學資訊工程學系學位論文 (2016): 1-49.
    [19] Hong, Wien, and Tung-Shou Chen. "Reversible data embedding for high quality images using interpolation and reference pixel distribution mechanism." Journal of Visual Communication and Image Representation 22.2 (2011): 131-140.
    [20] Li, C-T. "Digital fragile watermarking scheme for authentication of JPEG images." IEE proceedings-vision, image and signal processing 151.6 (2004): 460-466.
    [21] Tao, Hai, et al. "Robust image watermarking theories and techniques: A review." Journal of applied research and technology 12.1 (2014): 122-138.
    [22] Singh, Amritpal, and Harpal Singh. "An improved LSB based image steganography technique for RGB images." 2015 IEEE International Conference on electrical, computer and communication technologies (ICECCT). IEEE, 2015.
    [23] Kamel, Ibrahim, and Hussam Juma. "A lightweight data integrity scheme for sensor networks." Sensors 11.4 (2011): 4118-4136.
    [24] Ni, Zhicheng, et al. "Reversible data hiding." IEEE Transactions on circuits and systems for video technology 16.3 (2006): 354-362.
    [25] Roy, Sonjoy Deb, et al. "Hardware implementation of a digital watermarking system for video authentication." IEEE transactions on circuits and systems for video technology 23.2 (2012): 289-301.
    [26] Cheng, Chau-Jern, et al. "A fragile watermarking algorithm for hologram authentication." Journal of display technology 10.4 (2014): 263-271.
    [27] Wu, Min, and Bede Liu. "Watermarking for image authentication." Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No. 98CB36269). Vol. 2. IEEE, 1998.
    [28] Caragata, Daniel, et al. "Chaos based fragile watermarking algorithm for JPEG images." 2010 International Conference for Internet Technology and Secured Transactions. IEEE, 2010.
    [29] Chang, Chin-Chen, et al. "Reversible hiding in DCT-based compressed images." Information Sciences 177.13 (2007): 2768-2786.
    [30] Ural, Ozgur. "Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking." (2025).

    QR CODE