The problem unlearn_with_ease solves

•ML models may inadvertently memorize sensitive, unauthorized, or malicious data, leading to potential privacy breaches and security vulnerabilities.

• With the introduction of privacy laws like GDPR and CCPA, which include the "Right to be Forgotten," there's a pressing need for methods to remove specific user data from trained models.

•Removing or updating data in ML models often requires complete retraining, which is computationally expensive and time-consuming, especially for large models and datasets.

Challenges we ran into

Model is taking time to unlearn as it's run on CPU
Could've been faster if done on GPU