DECISION-MAKING IN CLOUD SECURITY MANAGEMENT USING AI-BASED ANOMALY DETECTION: A SOCIAL SCIENCES PERSPECTIVE

Abstract

The rapid migration of critical organizational infrastructure to cloud environments has precipitated a fundamental shift in security operations, necessitating a reliance on Artificial Intelligence (AI) and Machine Learning (ML) for anomaly detection. As cloud architectures evolve into ephemeral, microservices-based ecosystems, the volume of telemetry data surpasses human cognitive processing capabilities, positioning AI not merely as a tool but as a requisite agent of surveillance. While technical discourse predominantly prioritizes detection accuracy, latency reduction, and computational efficiency, the sociotechnical implications of these systems on human decision-making remain critically under-theorized. This study examines AI-based anomaly detection not as a neutral technical instrument, but as a potent socio-technical influence mechanism that reconfigures organizational judgment, authority, and power. Adopting an interpretive lens grounded in sociotechnical systems theory, sensemaking, and institutional theory, the research investigates how algorithmic outputs shape human interpretation of risk, renegotiate the locus of decision authority, and alter governance structures. The analysis reveals that AI-driven anomaly detection introduces a "black-box" authority that can erode human epistemic confidence, necessitating new frameworks for accountability where decision-making power is shared between human analysts and opaque algorithms. Furthermore, it identifies a phenomenon of "liability shielding," where reliance on algorithmic outputs serves as a defensive mechanism against organizational blame. This article contributes to the information systems and organizational studies literature by conceptualizing the shift from human-centric security management to a hybrid, algorithmically mediated governance model, offering a theoretical roadmap for navigating the paradoxes of automated security