Increasing the detection ability of unknown attack types

The gap

Evidence profile

Sourced from the limitations and future work and future-work section of the source papers, classified as general, drawn from work published between 2024 and 2026, spanning 3 journals. Those papers have been cited 131 times in total.

Supporting evidence — 3 representative gaps

• Enhancing DDoS Attack Detection and Mitigation in SDN Using an Ensemble Online Machine Learning Model (2024) · IEEE Access · cited 115× · doi

  detecting OML excels in mitigating the challenges posed by ever- changing data distributions and concept drift, frequent adversaries in network security. It effortlessly adapts to shifting network behavior and extends the capability of proactive threat detection, even when faced with previously unseen attack patterns. E. Ensemble machine learning model Ensemble learning, a potent approach in machine learning, involves the incorporation of multiple models to create a more resilient and accurate predictive system [35]. The core concept revolves around leveraging the strengths of diverse models to compensate for individual weaknesses, ultimately enhancing the overall predictive performance. This collaborative strategy reduces overfitting risks and captures nuanced patterns in the data, making ensemble models particularly effective across a range of applications [36]. Ensemble models come in various types, each with its unique methodology. Bagging, exemplified by Random Forests, concurrently trains multiple models on different subsets of the training data to generate a robust aggregate prediction. Boosting techniques, such as AdaBoost and Gradient Boosting, sequentially train models, emphasizing instances that were previously misclassified to improve overall accuracy. Additionally, stacking combines predictions from multiple models using a meta-learner, aiming to leverage the diverse strengths of individual models for a more comprehensive outcome [36].

  generallimitationsevidence 5/5
  Keywords: models ensemble learning multiple concept network previously patterns machine predictive strengths diverse individual overall boosting
• Hybrid ANN–DNN–LSTM Deep Learning Architecture for Botnet Detection in Smart Grid Cyber-Physical Systems (2026) · Journal of Science Innovation and Technology Research · doi

  Even with these promising findings, there are still a number of areas that may be investigated further. First, the hybrid ensemble framework's practical applicability and scalability would be further demonstrated by real-time deployment and validation in live or hardware-in-the- loop smart grid systems. Second, in order to dynamically modify model contributions in response to changing assault patterns, future research may investigate adaptive ensemble weighting techniques and online learning methods. Additionally, by offering interpretable insights into detection choices, using explainable AI (XAI) approaches might increase model transparency and operator confidence. REFERENCES Abbassy, M. M., Satya Sai Kumar, A., Ead, W. M., Mohamed Aboalndr, A. A., Alsheref, F. K., Abdalla, M., & Shivani, A. (2025). Hybrid deep learning framework for detection of anomalies in cyber-physical systems. International Journal of Information Technology. https://doi.org/10.1007/s41870-025-02633-7 Alguliyev, R., Imamverdiyev, Y., & Sukhostat, L. (2021). Hybrid DeepGCL model for cyber-attacks detection on cyber-physical systems. Neural Computing and Applications, 33(16), 10211–10226. https://doi.org/10.1007/s00521-021-05785-2 Alomari, M. A., Al-Andoli, M. N., Ghaleb, M., Thabit, R., Alkawsi, G., Alsayaydeh, J. A. J., & Gaid, A. S. (2025). Security of smart grid: cybersecurity issues, potential cyberattacks, major incidents, and future directions. Energies, 18(1), 141. Arumugam, S. R., Paul, P. M., Issac, B. J. J., & Ananth, J. P. (2024). Hybrid deep architecture for intrusion detection in cyber- physical system: An optimization-based approach. International Journal of Adaptive Control and Signal Processing, 38(9), 3016–3039. https://doi.org/10.1002/acs.3855 Bhuiyan, T. (2025). AI in Smart Grid Cybersecurity: A Systematic Review of Machine Learning and Deep Learning Approaches against False Data Injection and Other Emerging Attacks. Journal of Computer Science and Technology Studies, 7(8), 1207- 1295. Bitirgen, K., & Filik, Ü. B. (2023). A hybrid deep learning model for discrimination of physical disturbance and cyber-attack Infrastructure Protection, 40, Article 100582.

  generalfuture workevidence 5/5
  Keywords: hybrid learning cyber model detection deep physical smart grid systems journal https further ensemble framework
• A Lightweight Intrusion Detection System with Dynamic Feature Fusion Federated Learning for Vehicular Network Security (2025) · Sensors · cited 16× · doi

  increase the detection ability of unknown attack types, - improve the generalization ability of the model to unknown threats by introducing unsupervised learning or semi-supervised learning mechanisms, - carry out more comprehensive simulation experiments and actual deployment tests to evaluate the real-time performance, stability and robustness of the model in the real environment, - explore a more refined adaptive weight adjustment mechanism to further optimize the efficiency and effectiveness of feature fusion between nodes in the federated learning framework, - extend the framework to detect unknown or evolving threat patterns in broader autonomous vehicle network scenarios

  generalfuture-work sectionevidence 5/5
  Keywords: increase detection ability unknown attack types improve generalization

Questions about this gap