본문 바로가기
  • Home

A Comparative Study and Performance Analysis of Adversarial Watermarking Techniques

  • Journal of Software Assessment and Valuation
  • Abbr : JSAV
  • 2024, 20(4), pp.81-89
  • Publisher : Korea Software Assessment and Valuation Society
  • Research Area : Engineering > Computer Science
  • Received : October 11, 2024
  • Accepted : December 20, 2024
  • Published : December 31, 2024

Ji-Hun Kim 1 Seok-Min Hong 2 Yongtae Shin 1

1숭실대학교
2숭실대

Accredited

ABSTRACT

Due to the rapid spread of OTT platforms and the increase in digital content consumption, the importance of preventing illegal copying of content is being emphasized more. AI technology is positioned as a key tool in content protection and management. However, the development of AI technology has the potential to be used with malicious intent. As for copyright infringement using AI, watermark removal is typical. Deep learning technology is mainly used to remove watermarks using AI. Adversarial watermarks are attracting attention as a countermeasure to watermark removal using AI. However, it is difficult to know which method of implementing adversarial watermarks between various adversarial watermark technologies is most efficient. Therefore, in this paper, a comparative study and performance analysis of adversarial watermark technology are conducted.

Citation status

* References for papers published after 2023 are currently being built.