AI-synthesized faces are indistinguishable from real faces and more trustworthy 论文
2022Proceedings of the National Academy of Sciences引用 332
Face recognition and analysisGenerative Adversarial Networks and Image SynthesisLaw in Society and Culture
详细信息
- 发表期刊/会议
- Proceedings of the National Academy of Sciences
- 发表日期
- 2022-02-14
- 发表年份
- 2022
关键词
Face recognition and analysisGenerative Adversarial Networks and Image SynthesisLaw in Society and Culture
摘要
Artificial intelligence (AI)-synthesized text, audio, image, and video are being weaponized for the purposes of nonconsensual intimate imagery, financial fraud, and disinformation campaigns. Our evaluation of the photorealism of AI-synthesized faces indicates that synthesis engines have passed through the uncanny valley and are capable of creating faces that are indistinguishable-and more trustworthy-than real faces.