Are you for real? Decoding realistic AI-generated faces from neural activity

Can we trust our eyes? Until recently, we rarely had to question whether what we see is indeed what exists, but this is changing. Artificial neural networks can now generate hyperrealistic images that challenge our perception of what is real. This new reality can have significant implications in cybersecurity, counterfeiting, fake news, and border security. We investigated how the human brain encodes and interprets hyperrealistic artificially generated images using behaviour and brain imaging. We found that we could reliably detect AI-generated fake images using people’s brain activity, even though people could not consciously report seeing differences between real and fake images. Understanding this dissociation between brain and behaviour may be key in determining the 'real' in our new reality.

能否信赖我们的双眼？直至近期，我们鲜少质疑我们所见是否确为存在之物，然而这一状况正在改变。人工神经网络现已能够生成超逼真的图像，挑战我们对现实之真实性的感知。这一新的现实可能对网络安全、假币制造、虚假新闻以及边境安全产生重大影响。我们探究了人类大脑如何通过行为和脑成像来编码和解读超逼真的由人工生成的图像。我们发现，尽管人们无法有意识地报告出真实与虚假图像之间的差异，但我们仍能可靠地通过人们的脑活动来检测AI生成的虚假图像。理解大脑与行为之间的这种分离或许是我们确定新现实中的‘真实’的关键。