POROUS-SHIELD: Multi-Layer Cybersecurity Framework for Real-Time Threat Detection and SOC Automation

DOI

10.2991/978-94-6239-789-7_17How to use a DOI?

Keywords

Threat Scoring; Intrusion Detection; Anomaly Detection; Network Security; Multi-Layer Detection; Cybersecurity; CICIDS2017; Explainable AI

Abstract

POROUS-SHIELD is an interaction-sensitive multi-layer architecture for real-time intrusion detection in complex enterprise systems, introduced in this paper. The detection in the proposed approach is formulated as a context-sensitive risk inference problem on heterogeneous and time-varying security signals, as opposed to the more traditional intrusion detection systems which depend on independent and point-wise classification. The model integrates rule-based detection, anomaly detection and behavioural analysis into a single architecture. To model interdependences between the different security indicators, the framework proposes a threat scoring system that is interaction conscious. Besides, it introduces a temporal risk propagation method that detects multi-stage and low-intensity attacks that other systems are likely to disregard. The proposed model is tested on the CICIDS2017 dataset and is found to have a detection rate of 93.2%, F1-score of 0.925, and a lower false positive rate in comparison with the baseline methods. It is designed for Security Operations Centre (SOC) environments and provides scalable, robust and interpretable intrusion detection for imbalanced data scenarios. Overall, POROUS-SHIELD is capable of bringing intrusion detection to a new stage of interaction-sensitive risk inference, moving beyond static classification, for current cybersecurity applications.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Abhinav Narain
AU  - Vijay Laxmi
AU  - Shefali Bisht
AU  - Vishal Painuly
AU  - Akhil Mishra
PY  - 2026
DA  - 2026/10/08
TI  - POROUS-SHIELD: Multi-Layer Cybersecurity Framework for Real-Time Threat Detection and SOC Automation
BT  - Proceedings of theInternational Conference on Innovation and Practices in Artificial Intelligence (ICIPAI 2026)
PB  - Atlantis Press
SP  - 236
EP  - 250
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-789-7_17
DO  - 10.2991/978-94-6239-789-7_17
ID  - Narain2026
ER  -