Today’s business organizations need access control systems that can handle complex, changing security requirements that go beyond what traditional methods can manage. Current approaches, such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), and Discretionary Access Control (DAC), were designed for specific purposes. They cannot effectively manage the dynamic, situation-dependent workflows that modern systems require. In this research, we introduce LLMAC, a new unified approach using Large Language Models (LLMs) to combine these different access control methods into one comprehensive, understandable system. We used an extensive synthetic dataset that represents complex real-world scenarios, including policies for ownership verification, version management, workflow processes, and dynamic role separation. Using Mistral 7B, our trained LLM model achieved outstanding results with 98.5% accuracy, significantly outperforming traditional methods (RBAC: 14.5%, ABAC: 58.5%, DAC: 27.5%) while providing clear, human readable explanations for each decision. Performance testing shows that the system can be practically deployed with reasonable response times and computing resources.

Interaction provenance refers to the documentation of every action and interaction within a system, including detailed metadata such as the actor’s identity, the time the action occurred, and the surrounding context of the interaction [1] . This concept is important for understanding the history and origins of data and processes, providing a transparent and traceable record of all activities within a system specially privacy-aware systems.

Detecting vulnerabilities in smart contracts presents a significant challenge due to the unique nature of the vulnerabilities and the complexity of contract codes [3]. Existing approaches, which include formal verification, symbolic execution, machine learning (ML), and deep learning (DL), often struggle with issues of accuracy, transparency, and the ability to adapt to new threats [6]. This research introduces an innovative system that employs graph-based feature extraction alongside ML-based prediction to improve the identification of vulnerabilities in Ethereum smart contracts [1].