Description
Teams from IBM labs in Haifa and Dublin have developed software to help assess privacy risk of AI and reduce the amount of personal data in AI training.
Summary
- Privacy is vital – even more so in the modern era of AI.
- Our team of researchers from IBM Haifa and Dublin has developed software to help assess privacy risk of AI as well as reduce the amount of personal data in AI training.
- Applied during the training process, DP could limit the effect of anyone’s data on the model’s output.
- Accuracy-guided anonymization That’s where anonymization can be handy – applied to the data before training the model.