2022/08/23 by Alexander Becker, Becker, Alexander, Thomas Liebig +1 · 5 citations
Computer Science · #Adversarial Robustness in Machine Learning #Distributed Sensor Networks and Detection Algorithms #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #I.2.6 #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2208.10836
openalex publication_date 2022/08/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
There has been a growing interest in Machine Unlearning recently, primarily due to legal requirements such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act. Thus, multiple approaches were presented to remove the influence of specific target data points from a trained model. However, when evaluating the success of unlearning, current approaches either use adversarial attacks or compare their results to the optimal solution, which usually incorporates retraining from scratch. We argue that both ways are insufficient in practice. In this work, we present an evaluation metric for Machine Unlearning algorithms based on epistemic uncertainty. This is the first definition of a general evaluation metric for Machine Unlearning to our best knowledge.