Enhancing Autonomous Online Intrusion Detection for IoT with Balanced Learning, Reliable Pseudo-Labels, and Lightweight Architectures
arXiv:2605.26166v1 Announce Type: cross Abstract: The rapid proliferation of Internet of Things (IoT) devices has created an urgent demand for adaptive, resource-efficient Intrusion Detection Systems (IDS) capable of handling dynamic and evolving cyber threats. This paper investigates AOC-IDS, a state-of-the-art autonomous online IDS published at IEEE INFOCOM 2024, which employs an Autoencoder (AE) with Cluster Repelling Contrastive (CRC) loss and an autonomous Gaussian-based decision module. We first successfully replicate AOC-IDS on the UNSW-NB15 benchmark, achieving 89.39% accuracy in close
The rapid proliferation of IoT devices and increasing cyber threats necessitate immediate and adaptive security solutions, leading to advancements in autonomous intrusion detection.
This research addresses the critical vulnerability of IoT ecosystems, proposing a more resilient and resource-efficient security framework, which is vital for the widespread adoption and reliability of IoT.
The development of more effective and autonomous intrusion detection systems for IoT mitigates significant security risks, enhancing the integrity and trustworthiness of interconnected devices.
- · IoT device manufacturers
- · Cybersecurity firms
- · Critical infrastructure relying on IoT
- · Consumers of IoT devices
- · Cyber attackers
- · Legacy intrusion detection systems
Increased security and reliability of IoT deployments.
Faster adoption of IoT in sensitive sectors due to enhanced trust.
Reduced cyber insurance premiums for IoT-dependent enterprises as risks diminish.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG