GCTAuto-encoder: A Cross modal Framework for Security Flaw Detection in IoT Networks
GCT auto-encoder reports 0.908 accuracy detecting IoT network intrusions from edge data.
The paper proposes GCTAuto-encoder, a cross-modal deep learning framework for detecting intrusions and security flaws in heterogeneous IoT networks, using edge intelligence with a cloud-based IoT setup. The model is a cross-domain DNN that applies community detection with modeled attention to local edge data. On a network-intrusion IoT dataset covering multiple attack scenarios, the authors report 0.908 accuracy and learning loss of 0.00156, outperforming the baselines they compared.
- Cross-modal auto-encoder targets IoT intrusion detection at the edge.
- Uses attention and community detection inside a DNN.
- Reported 0.908 accuracy and 0.00156 learning loss.
- Evaluated on a multi-attack IoT network intrusion dataset.
From the original article
1 min read at arxiv.orgIoT encompasses diverse physical entities, from smart home devices to autonomous vehicles, creating a complex environment with heterogeneous security models. This heterogeneity makes IoT sub-systems vulnerable to various network attacks. Modern security systems must therefore be more robust to ensure security and privacy for IoT applications.
By Najmieh Sadat Safarabadi · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.