정보처리학회 논문지 (The Transactions of the Korea Information Processing Society)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

오류 정정 부호를 결합한 계층적 워터마킹 기법

Hierarchical Watermarking Technique Combining Error Correction Codes

  • 김도은 (성신여자대학교 융합보안공학과) ;
  • 박소현 (성신여자대학교 미래융합기술공학과) ;
  • 이일구 (성신여자대학교 융합보안공학과/미래융합기술공학과)
  • 투고 : 2024.07.11
  • 심사 : 2024.09.06
  • 발행 : 2024.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

디지털 워터마킹은 디지털 컨텐츠에 정보를 삽입하는 기술이다. 불법 복제 근절과 인공지능이 생성한 콘텐츠 식별 기술로 디지털 워터마킹이 주목받고 있지만, 여전히 다양한 상황에서 견고하지 못하다. 본 논문에서는 공격 탐지와 오류 정정 및 소유자 식별이 가능한 주파수 변환 기반의 계층적 워터마킹 기법을 제안한다. 제안 방식은 계층적 워터마킹에 공격 탐지 및 오류 정정 시그니처 삽입을 통해 비가시성을 유지하며 용량과 견고성 측면에서 종래 방법보다 향상된 성능을 보였다. 또한 오류정정부호 종류와 시그니처 삽입 횟수에 따른 이미지 품질과 오류정정 성능을 비교 평가하는 프레임워크를 제안하여, 오류정정부호가 없는 종래 모델과 해밍 부호 및 BCH 부호를 적용한 종래 모델의 시각적 품질과 오류정정 성능을 비교 평가하였다. 시그니처 삽입 횟수에 따른 품질을 비교한 결과에 따르면 삽입 횟수가 증가할수록 품질은 열화되나 공격 상황에 견고하였다. 그리고 오류정정부호 종류에 따른 품질과 오류 정정 능력을 분석한 결과에 따르면 BCH 부호보다 해밍 부호 사용 시 향상된 오류정정 성능을 보였으며, 종래 방식 대비 41.31% 향상된 시그니처 복원 성능을 보였다.

Digital watermarking is a technique for embedding information into digital content. Digital watermarking has attracted attention as a technique to combat piracy and identify artificially generated content, but it is still not robust in various situations. In this paper, we propose a frequency conversion-based hierarchical watermarking technique capable of attack detection, error correction, and owner identification. By embedding attack detection and error correction signatures in hierarchical watermarking, the proposed scheme maintains invisibility and outperforms the existing methods in capacity and robustness. We also proposed a framework to evaluate the performance of the image quality and error correction according to the type of error correction signature and the number of signature embeddings. We compared the visual quality and error correction performance of the conventional model without error correction signature and the conventional model with hamming and BCH signatures. We compared the quality by the number of signature embeddings and found that the quality deteriorates as the number of embeddings increases but is robust to attacks. By analyzing the quality and error correction ability by error correction signature type, we found that hamming codes showed better error correction performance than BCH codes and 41.31% better signature restoration performance than conventional methods.

키워드

과제정보

이 논문은 2024년도 산업통상자원부 및 한국산업기술진흥원의 산업혁신인재성장지원사업 (RS-2024-00415520)과 과학기술정보통신부 및 정보통신기획평가원의 ICT혁신인재4.0 사업의 연구결과로 수행되었음(No. IITP-2022-RS-2022-00156310).

참고문헌

  1. A. Ray and S. Roy, "Recent trends in image watermarking techniques for copyright protection: a survey," International Journal of Multimedia Information Retrieval, Vol.9, No.4, pp.249-270, 2020. 
  2. H. R. Hasan, K. Salah, R. Jayaraman, I. Yaqoob, and M. Omar, "NFTs for combating deepfakes and fake metaverse digital contents," Internet of Things, Vol.25, p.101133, 2024. 
  3. M. Fenwick and P. Jurcys, "Originality and the Future of Copyright in an Age of Generative AI," Computer Law & Security Review, Vol.51, pp.105892, 2023. 
  4. J. Kim, D. Im, and H. Cha, "Legislative Study on Directions Concerning Regulation of Generative Artificial Intelligence (AI) Systems - Focusing on Duty to Disclosure and Transparency Regarding the Creations of Generative AI Systems Such as ChatGPT," Contemporary Review of Criminal Law, Vol.80, pp.245-283, 2023. 
  5. C. Novelli, F. Casolari, P. Hacker, G. Spedicato, and L. Floridi, "Generative AI in EU law: liability, privacy, intellectual property, and cybersecurity," arXiv preprint arXiv: 2401.07348, 2024. 
  6. S. Wadhera, D. Kamra, A. Rajpal, A. Jain, and V. Jain, "A comprehensive review on digital image watermarking," arXiv preprint arXiv:2207.06909, 2022. 
  7. O. Evsutin and K. Dzhanashia, "Watermarking schemes for digital images: Robustness overview," Signal Processing: Image Communication, Vol.100, pp.116523, 2022. 
  8. A. Mohanarathinam, S. Kamalraj, G. K. D. Prasanna Venkatesan, R. V. Ravi, and C. S. Manikandababu, "Digital watermarking techniques for image security: a review," Journal of Ambient Intelligence and Humanized Computing, Vol.11, No.8, pp.3221-3229, 2020. 
  9. M. Begum and M. S. Uddin, "Digital Image Watermarking Techniques: A Review," Information, Vol.11, No.2, pp.110, 2020. 
  10. S. M. Arora, "A DWT-SVD based robust digital watermarking for digital images," Procedia Computer Science, Vol.132, pp.1441-1448, 2018. 
  11. G. Coatrieux, L. Lecornu, B. Sankur, and C. Roux, "A Review of Image Watermarking Applications in Healthcare," in 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, pp.4691-4694, 2006. 
  12. S. Ranjbar Alvar, M. Akbari, D. Yue, and Y. Zhang, "NFT-Based Data Marketplace with Digital Watermarking," in Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp.4756-4767, 2023. 
  13. J. Yu, "Based on Gaussian filter to improve the effect of the images in Gaussian noise and pepper noise," Journal of Physics: Conference Series, Vol.2580, No.1, pp.012062, 2023. 
  14. T. Y. Goh, S. N. Basah, H. Yazid, M. J. A. Safar, and F. S. A. Saad, "Performance analysis of image thresholding: Otsu technique," Measurement, Vol.114, pp.298-307, 2018. 
  15. N. S. Hashemi, R. B. Aghdam, A. S. B. Ghiasi, and P. Fatemi, "Template matching advances and applications in image analysis," arXiv preprint arXiv:1610.07231, 2016. 
  16. Q. Cao, L. Qingge, and P. Yang, "Performance Analysis of Otsu-Based Thresholding Algorithms: A Comparative Study," Journal of Sensors, Vol.2021. No.1, pp.4896853, 2021. 
  17. A. Joseph and K. Anusudha, "Robust watermarking based on DWT SVD," International Journal on Signal & Image Security, Vol.1, No.1, pp.1-5, 2013. 
  18. D. Kim, S. Park, and I. Lee, "Hierarchical watermarking technique for detecting digital watermarking attacks," Proceedings of the Annual Symposium of Korea Information Processing Society Conference (KIPS), Vol.31, No.1, pp.283-284, 2024. 
  19. S. Kim, Y. Jeon, and I. Lee, "Robust digital watermarking technique against distortion attacks," Proceedings of the Annual Symposium of Korea Information Processing Society Conference (KIPS), Vol.31, No.1, pp.345-346, 2024.