Deepfakes are a serious problem. It’s now relatively easy to create speech, images or videos that give the strong impression of being real recordings of people, even though they are made up. By using images of peoples faces (particularly from videos) and recordings of the speaking it is possible to create very lifelike “recordings” of them speaking or acting. This is oiften seen as downside of Artificial Intelligence, but it has little to do with intelligence, and much more to do with engineering a basis of functions that can be combined to produce realistic data. [Is this intelligence? Maybe…]
I asked Bard what ir thought about the law and deepfakes
Can creators or publishers of damaging deepfakes be prosecuted under defamation laws?
and here’s the answer it gave:
Whether creators or publishers of damaging deepfakes can be prosecuted under defamation laws is a complex legal question with no easy answer. It depends on a variety of factors, including the specific jurisdiction, the content of the deepfake, and the intent of the creator or publisher.
Arguments for prosecution under defamation laws:
- Deepfakes can be just as damaging as traditional defamation: They can harm someone’s reputation, lead to lost job opportunities, and even cause emotional distress.
- Deepfakes are often used with malicious intent: They can be created to spread misinformation, damage someone’s reputation, or even extort money.
- Defamation laws are designed to protect people’s reputations: They should apply to deepfakes just as they do to traditional forms of defamation.
Gavel and sound block (image)
Arguments against prosecution under defamation laws:
- Deepfakes are often difficult to distinguish from real videos: This can make it hard to prove that a deepfake is actually defamatory.
- Defamation laws are intended to protect against false statements: If a deepfake is based on real events, it may not be considered defamatory even if it is damaging.
- Prosecution of deepfakes could infringe on freedom of speech: There is a concern that laws against deepfakes could be used to censor legitimate criticism or satire.
The current state of the law:
- There is no specific law against deepfakes in most jurisdictions. However, some countries are considering or have already passed laws that could be used to prosecute the creators or publishers of damaging deepfakes.
- In the United States, for example, some states have laws against cyberbullying and revenge porn, which could be used to prosecute the creators of deepfakes that are used to harass or humiliate someone.
- In the European Union, the General Data Protection Regulation (GDPR) gives people the right to control their personal data, which could be used to argue that deepfakes that use someone’s image without their consent are illegal.
Conclusion:
The legal landscape surrounding deepfakes is still evolving. It is likely that we will see more laws and court cases in the coming years that will help to clarify whether or not the creators and publishers of damaging deepfakes can be prosecuted under defamation laws.
I hope this information is helpful. Please let me know if you have any other questions.
There’s been a fair amount of discussion on this from the legal establishment:
https://www.farrer.co.uk/news-and-insights/ahead-of-the-algorithms-deepfakes-and-the-law/
https://www.nelsonslaw.co.uk/artificial-intelligence-deepfakes/
https://www.ashfords.co.uk/insights/articles/deep-fake-meets-real-law
https://lawdit.co.uk/readingroom/can-defamation-be-used-to-protect-victims-of-deepfakes-part-2
https://www.farrer.co.uk/news-and-insights/the-legal-issues-surrounding-deepfakes-and-ai-content/
(Thanks to LF for these)
What really hits me from all this is that the law takes a long time to catch up with new developments. The issue of anonymous posting makes prosecution very difficult. The ease with which the companies which share posts can get away with washing their hands of any responsibility is, to me, indefensible.
I don’t know the way forward: but eventually the law needs to catch up.
Lestheprof's Blog 