Scholarlink

<p>Generative artificial intelligence (AI) is advancing rapidly, with deepfake technology illustrating the intersection of AI and multimedia forensics. This study examines the classification and evolution of deepfake, exploring their definition, societal impact, advantages, challenges, and future potential. It traces the development of deepfake from early techniques to modern generative models and analyzes the role of large language models (LLMs) in their creation and detection. The study also emphasizes the emerging role of large vision-language models (LVLMs) in enhancing multimodal deepfake detection. By categorizing deepfake advancements and their enabling AI technologies, this research offers a structured framework for researchers and practitioners. Additionally, it highlights critical risks, including misinformation and the erosion of public trust. To address these concerns, the study advocates for a multidisciplinary mitigation strategy, combining technical, ethical, and policy-based approaches, along with a proposed prevention framework.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Generative AI and the rise of deepfake technology: a journey from traditional techniques to LLM integration

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月28日

查看全文
  • Fariha Jahan,
  • Sirajum Munira Shifat,
  • Md. Kishor Morol,
  • Nafiz Fahad,
  • Kah Ong Michael Goh,
  • Dip Nandi,
  • Md. Abdullah-Al-Jubair,
  • Md. Jakir Hossen

摘要

Generative artificial intelligence (AI) is advancing rapidly, with deepfake technology illustrating the intersection of AI and multimedia forensics. This study examines the classification and evolution of deepfake, exploring their definition, societal impact, advantages, challenges, and future potential. It traces the development of deepfake from early techniques to modern generative models and analyzes the role of large language models (LLMs) in their creation and detection. The study also emphasizes the emerging role of large vision-language models (LVLMs) in enhancing multimodal deepfake detection. By categorizing deepfake advancements and their enabling AI technologies, this research offers a structured framework for researchers and practitioners. Additionally, it highlights critical risks, including misinformation and the erosion of public trust. To address these concerns, the study advocates for a multidisciplinary mitigation strategy, combining technical, ethical, and policy-based approaches, along with a proposed prevention framework.