Newest papers

AIRO: A Streaming-Based Machine Learning Framework for Threat Detection and Security in Industrial Internet of Things

Raima Deb, Pranav Mothabhau Pawar, Mithun Mukherjee, Raja Muthalagu, Mian Guo · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30713 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Las implementaciones modernas de Internet Industrial de las Cosas (IIoT) ahora conectan las puertas del borde, los dashboards en la nube y las aplicaciones de negocios. Esto mejora la visibilidad y la vigilancia remota. Sin embargo, simultáneamente expone el tráfico industrial a diversas amenazas cibernéticas, incluyendo escaneo, ataques web y inyección de lenguaje de consulta estructurada (SQL) (SQLi), robo de credenciales impulsado por phishing y actividad de control y control (C2). Aunque las herramientas basadas en reglas siguen siendo útiles para detectar firmas conocidas, su eficacia disminuye con ataques modificados al mínimo o cuando las alertas requieren una investigación manual. Este documento presenta AIRO (Autonomic Intelligence-Driven Cybersecurity Credential Stealing Duction System),

Machine translation (Meta M2M100); the English original follows.

Abstract

Modern Industrial Internet of Things (IIoT) im- plementations now connect edge gateways, cloud dashboards and business applications. This improves visibility and remote monitoring. However it simultaneously exposes industrial traffic to various cyber threats including scanning, web attacks and Structured Query Language (SQL) injection (SQLi), phishing- driven credential theft, and command-and-control (C2) activity. Although rule-based tools remain useful for detecting known signatures, their efficacy decreases with minimally altered attacks or when alerts require manual investigation. This paper presents AIRO (Autonomous Intelligence-Driven Cybersecurity Risk Re- duction System), an efficient framework for IIoT monitoring and response. AIRO combines Apache Kafka streaming, attack- specific feature extraction, machine learning (ML) inference, confidence-based decision logic and risk reduction measures such as Internet Protocol (IP) blocking, account suspension and traffic limiting. We developed four specialized datasets for C2 beaconing, reconnaissance, SQLi, and phishing to evaluate AIRO. These datasets include noisy and overlapping characteristic distribu- tions to minimize label leakage. The best-performing models, primarily Gradient Boosting and LightGBM, achieve F1-scores up to 0.9229 while ensuring low-latency from event input to mitigation

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Computer security, The Internet, Cloud computing, Credential, Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange