When you fine-tune a model on a specific task, it inadvertently memorises parts of the training data β including sensitive information. STAMP detects and suppresses this task-irrelevant memorisation during training, preventing privacy leakage without hurting task performance. Increasingly essential as data-use regulations tighten globally and training data audits become standard.
Comments on "STAMP: Selective Task-Aware Mechanism for Text Privacy"
Create a free account or sign in to join the discussion.
Sign in to join the conversation