Saved in:
Bibliographic Details
Main Authors: Banerjee, Sourasekhar, Bergqvist, David, Toor, Salman, Rohner, Christian, Johnsson, Andreas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.00363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918361388023808
author Banerjee, Sourasekhar
Bergqvist, David
Toor, Salman
Rohner, Christian
Johnsson, Andreas
author_facet Banerjee, Sourasekhar
Bergqvist, David
Toor, Salman
Rohner, Christian
Johnsson, Andreas
contents Distribution shifts in attack patterns within RPL-based IoT networks pose a critical threat to the reliability and security of large-scale connected systems. Intrusion Detection Systems (IDS) trained on static datasets often fail to generalize to unseen threats and suffer from catastrophic forgetting when updated with new attacks. Ensuring continual adaptability of IDS is therefore essential for maintaining robust IoT network defence. In this focused study, we formulate intrusion detection as a domain continual learning problem and propose a method-agnostic IDS framework that can integrate diverse continual learning strategies. We systematically benchmark five representative approaches across multiple domain-ordering sequences using a comprehensive multi-attack dataset comprising 48 domains. Results show that continual learning mitigates catastrophic forgetting while maintaining a balance between plasticity, stability, and efficiency, a crucial aspect for resource-constrained IoT environments. Among the methods, Replay-based approaches achieve the best overall performance, while Synaptic Intelligence (SI) delivers near-zero forgetting with high training efficiency, demonstrating strong potential for stable and sustainable IDS deployment in dynamic IoT networks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00363
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quantifying Catastrophic Forgetting in IoT Intrusion Detection Systems
Banerjee, Sourasekhar
Bergqvist, David
Toor, Salman
Rohner, Christian
Johnsson, Andreas
Machine Learning
Artificial Intelligence
Distribution shifts in attack patterns within RPL-based IoT networks pose a critical threat to the reliability and security of large-scale connected systems. Intrusion Detection Systems (IDS) trained on static datasets often fail to generalize to unseen threats and suffer from catastrophic forgetting when updated with new attacks. Ensuring continual adaptability of IDS is therefore essential for maintaining robust IoT network defence. In this focused study, we formulate intrusion detection as a domain continual learning problem and propose a method-agnostic IDS framework that can integrate diverse continual learning strategies. We systematically benchmark five representative approaches across multiple domain-ordering sequences using a comprehensive multi-attack dataset comprising 48 domains. Results show that continual learning mitigates catastrophic forgetting while maintaining a balance between plasticity, stability, and efficiency, a crucial aspect for resource-constrained IoT environments. Among the methods, Replay-based approaches achieve the best overall performance, while Synaptic Intelligence (SI) delivers near-zero forgetting with high training efficiency, demonstrating strong potential for stable and sustainable IDS deployment in dynamic IoT networks.
title Quantifying Catastrophic Forgetting in IoT Intrusion Detection Systems
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.00363