Knowledge Distillation-Based Model Extraction Attack using Private Counterfactual Explanations

arXiv:2404.03348v1 Announce Type: new
Abstract: In recent years, there has been a notable increase in the deployment of machine learning (ML) models as services (MLaaS) across diverse production software applications. In parallel, explainable AI (XAI) continues to evolve, addressing the necessity for transparency and trustworthiness in ML models. XAI techniques aim to enhance the transparency of ML models by providing insights, in terms of the model's explanations, into their decision-making process. Simultaneously, some MLaaS platforms now offer explanations alongside the …

abstract aim applications arxiv counterfactual cs.ai cs.cr cs.cy cs.lg deployment distillation diverse explainable ai extraction knowledge machine machine learning ml models production services software software applications transparency type xai