An Effective Neural Network Model Protection Method Against Model Stealing Attacks for Image Classification Applications

The growing adoption of Deep Learning (DL) models at the network edge necessitates robust security measures. Image preprocessing, a common technique for securing DL models, often involves shuffling the pixels of training images before feeding them to the model. In this work, we found that the shuffle-then-flip method offers superior resilience compared to the shuffle-only method. We also investigate the effectiveness of the shuffle-then-flip preprocessing technique in enhancing the security of models against attacks.