Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation

arXiv:2403.07673v1 Announce Type: new
Abstract: Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a severe threat to the security and integrity of pay-per-query DNN-based services. Although the majority of current research on MEAs has primarily concentrated on neural classifiers, there is a growing prevalence of image-to-image translation (I2IT) tasks in our everyday activities. However, techniques developed for MEA of DNN classifiers …

api arxiv attacker attacks cs.cr domain enable extraction gan image integrity mitigation model extraction network neural network pay query security service services threat translation victim