Denoising Adaptive - Multi-Branch Architecture for Detecting Cyber Attacks in Industrial Internet of Services

The emerging scope of the Industrial Internet of Services (IIoS) requires a robust intrusion detection system to detect malicious attacks. Numerous robust and sophisticated cyberattacks have resulted in financial losses and catastrophes in IIoS-based manufacturing industries. However, existing solutions often struggle with adaptability and generalizability to emerging and sophisticated cyber-attacks. This study proposes a unique approach for adaptive deep learning pipelines tailored for zero-day network attack detection in Industrial Internet of Services (IIoS) environments. The proposed approach merges a denoising autoencoder (DAE), enhanced by an adaptively tuned noise factor, with a hybrid model based on MLP + BiLSTM named as DA-MBA (Denoising Adaptive - Multi-Branch Architecture). The DAE filters noise and learns robust representations, making subsequent classification less sensitive to benign concerns. Moreover, it addresses challenges, such as adaptability and generalizability, by hybridizing a Multilayer Perceptron (MLP) and bidirectional LSTM (BiLSTM). The proposed hybrid model was designed to fuse feed-forward transformations with sequence-aware modeling, which can capture direct feature interactions and any underlying temporal and order-dependent patterns. Multiple approaches have been applied to strengthen the dual-branch architecture, such as SMOTE-based oversampling, class weighting, and comprehensive hyperparameter optimization via Optuna, which collectively addresses imbalanced data, overfitting, and dynamically shifting threat vectors. The proposed DA-MBA is evaluated on two widely recognized IIoT-based datasets, Edge-IIoT set and WUSTL-IIOT-2021, and achieves over 99% accuracy and a near 0.02 loss, underscoring its effectiveness in detecting the most sophisticated attacks. The solution offers a scalable, flexible architecture for enhancing cybersecurity within evolving IIoS environments by coupling feature denoising, multi-branch classification, and automated hyperparameter tuning. The results confirm that coupling robust feature denoising with sequence-aware classification can provide a scalable and flexible framework for improving cybersecurity within the IIoS.