A team led by computer scientist Rongshan Yu from Xiamen University in China created a series of deepfake western blot and cancer images. Two out of three biomedical specialists were unable to distinguish them from the real thing. AI-generated ones could be almost impossible to detect by eye.

Figure 1: impossible to detect AI fake images.

Figure 1 shows that the problem is that deepfake images are unique, says Yu. They show none of the traces people usually look for – duplicated elements and background inconsistencies, for example. Moreover, ‘deepfake and other tools are now highly available’, says Yu. ‘It isn’t rocket science; you don’t need a top expert in AI to use them.’

Deepfakes are often based on generative adversarial networks (Gan), where a generator and a discriminator try to outcompete each other.

‘It doesn’t know how to generate a face initially, so it takes the help of a discriminator, which is another network that learns how to tell apart whether an image is real or fake.’ Eventually, the generator will fool the discriminator into thinking its images are real, said John (Saniat) Sohraward. [1]

while deepfakes are a threat to be taken seriously, I’m far more concerned about reproducibility, p-hacking, Photoshop manipulation – the old school stuff, which is still going to, I suspect, dominate for quite a while, said Berkeley.

Matthew Wright, director of the Rochester’s Global Cybersecurity Institute, agrees. ‘I just don’t find this to be particularly threatening, even though it’s technically quite possible and probably difficult to detect if someone did it.’ [2]

The digital artifacts left behind by machine learning could be used to identify fake images, Farid says, although fraudsters usually find a way around these methods after just a few months.

“At the end of the day, the only real solution are active solutions, authenticated with hard encryption at the time of registration,” says Farid. He believes that science’s self-correcting mechanisms will eventually weed out fake research.

Yu says it’s unclear whether the literature already contains AI-generated images. “I think we’ve reached the point where we can no longer tell whether the paper is real or fake,” Bik says. [3]

References:

1. https://www.chemistryworld.com/news/ai-generated-images-could-make-it-almost-impossible-to-detect-fake-papers/4015708.article
2. https://indiajustnow.in/technology/ai-generated-images-could-make-it-almost-impossible-to-detect-fake-papers/
3. https://theriskywriter.com/ai-generated-images-could-make-it-almost-impossible-to-detect-fake-papers-new/

Cite this article:

Sri Vasagi K (2022), Impossible to Detect AI Generated Fake Images, AnaTechMaz, pp.111