Learnability Lock: Authorized Learnability Control Through Adversarial Invertible TransformationsDownload PDF

29 Sept 2021, 00:32 (edited 03 Feb 2022)ICLR 2022 PosterReaders: Everyone
  • Abstract: Owing much to the revolution of information technology, recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digital formats. Yet those publicly accessible information also raises a fundamental issue concerning Intellectual Property, that is, how to precisely control legal or illegal exploitation of a dataset for training commercial models. To tackle this issue, this paper introduces and investigates a new concept called ''learnability lock'' for securing the process of data authorization. In particular, we propose adversarial invertible transformation, that can be viewed as a mapping from image to image, to encrypt data samples so that they become ''unlearnable'' by machine learning models with negligible loss of visual features. Meanwhile, authorized clients can use a specific key to unlock the learnability of the protected dataset and train models normally. The proposed learnability lock leverages class-wise perturbation that applies a universal transformation function on data samples of the same label. This ensures that the learnability can be easily restored with a simple inverse transformation while remaining difficult to be detected or reverse-engineered. We empirically demonstrate the success and practicability of our method on visual classification tasks.
24 Replies