Word-embedding Approach for Unknown Attributes in Access Control Model

With the rapid advancements in computing and information technologies, access control models have become increasingly essential as the first line of defense. However, many traditional methods require significant human intervention. While these rule-based approaches, crafted by experienced system engineers, are highly reliable, they are also time-consuming and dependent on human resources that may not always be available. As an alternative, the attribute-based access control (ABAC) model provides greater flexibility in addressing the authorization needs of complex and dynamic systems. Nevertheless, many existing approaches fail to capture the contextual meaning of attribute values, as they are typically treated as categorical data. This paper introduces a framework that leverages advanced Natural Language Processing (NLP) techniques to generate embedding vectors for attribute requests, utilizing a Skip-gram architecture to encode contextual relationships. By extracting well-defined features from these requests, a machine learning classifier is trained to determine authorization decisions accurately. We also explore a variation of the embedding method to accommodate newly introduced values within the system. Our experiments, conducted on real-world datasets, demonstrate the effectiveness of our approach by comparing it against State-of-the-Art (SOTA) models and evaluating its performance in evolving system scenarios. Finally, we discuss our method's advantages and challenges and suggest future research directions.