\u201cExisting methods rely on trial and error or assumptions about how AI models behave,\u201d he said. \u201cOur approach is different; we can mathematically guarantee that unauthorised machine learning models can\u2019t learn from the content beyond a certain threshold. That\u2019s a powerful safeguard for creators and organisations.\u201d<\/p>\n
Loading<\/p>\n
He said the technique could be applied automatically at scale: a social media platform, for example, could embed the protective layer into every image uploaded.<\/p>\n
\u201cThis could curb the rise of deepfakes, reduce intellectual property theft, and help users retain control over their content,\u201d he said.<\/p>\n
\u201cIt wasn\u2019t an easy task to achieve this. It\u2019s been a great challenge from a scientific perspective, and I think this is the first time that we have seen this kind of guarantee in the field.\u201d<\/p>\n
There are plans to expand the development to text, music and videos. The paper, Provably Unlearnable Data Examples, was presented at the 2025 Network and Distributed System Security Symposium, where it received the distinguished paper award.<\/p>\n
To date, the algorithm is still theoretical. Results are validated in a controlled lab setting, but the team has released the code on GitHub for academic use and is hoping to partner with researchers or the private sector to make it a commercial reality.<\/p>\n
\u201cI think this has great potential to transform the research in this field,\u201d Wang said.<\/p>\n