Secure Pipelines, Smarter AI: LLM-Powered Data Engineering for Threat Detection and Compliance
Year: 2025
Type: preprint
Abstract: As digital ecosystems become increasingly complex, safeguarding sensitive data while ensuring regulatory compliance poses a dual challenge. Traditional security systems often fall short in detecting nuanced threats or adapting to evolving attack vectors. In contrast, large language models (LLMs) offer a transformative approach—enabling intelligent threat detection through contextual analysis, anomaly interpretation, and adaptive rule learning. This paper proposes a hybrid data engineering framework that integrates LLMs into secure pipelines for real-time threat monitoring, compliance enforcement, and operational governance. We explore architectural models, performance benchmarks, and use cases demonstrating how LLMs elevate both security posture and auditability. Through comparative analysis and flow-based design, we highlight the future of resilient, AI-driven data engineering tailored for modern cybersecurity demands.
Source: Preprints.org
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4409587840