Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning

Understand

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains.

• However, this utility comes with increasing concerns about privacy, as the training data may include sensitive information.
• To address these concerns, machine unlearning has been proposed to erase specific data samples from models.
• While some unlearning techniques efficiently remove data at low costs, recent research highlights vulnerabilities where malicious users could request unlearning on manipulated data to compromise the model.