2022/02/03 by Weiqi Peng, Peng, Weiqi, Jinghui Chen +1
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.CR #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2202.03576
Accepted at ICLR 2022
arxiv created 2022/02/03 · openalex publication_date 2022/02/03 · arxiv updated 2022/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digital formats. However, in certain scenarios, people may not want their data being used for training commercial models and thus studied how to attack the learnability of deep learning models. Previous works on learnability attack only consider the goal of preventing unauthorized exploitation on the specific dataset but not the process of restoring the learnability for authorized cases. To tackle this issue, this paper introduces and investigates a new concept called "learnability lock" for controlling the model's learnability on a specific dataset with a special key. In particular, we propose adversarial invertible transformation, that can be viewed as a mapping from image to image, to slightly modify data samples so that they become "unlearnable" by machine learning models with negligible loss of visual features. Meanwhile, one can unlock the learnability of the dataset and train models normally using the corresponding key. 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.