Related Experiment Videos
TaWSA-WRN: a Taylor wave search optimized WideResNet framework for intrusion detection with response-aware mitigation
V Sahiti Yellanki1, Basant Sah2
1Department of Computer Science and Engineering, KL University, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur, AP, 522502, India. sahithivellanki@gmail.com.
Scientific Reports
|May 12, 2026
Summary
This study introduces a Taylor Wave Search Algorithm-optimised Wide Residual Network (TaWSA_WRN) for enhanced cloud intrusion detection. The novel framework improves accuracy and stability, offering robust protection against cyberattacks.
Area of Science:
- Cybersecurity
- Cloud Computing Security
- Machine Learning for Network Security
Background:
- Cloud environments are increasingly targeted by sophisticated cyberattacks.
- Traditional Intrusion Detection Systems (IDSs) using deep learning often face challenges like overfitting and high false-positive rates.
- Need for robust and interpretable intrusion detection in scalable, distributed cloud infrastructures.
Purpose of the Study:
- To introduce a novel framework, the Taylor Wave Search Algorithm-optimised Wide Residual Network (TaWSA_WRN), for intrusion detection and mitigation in cloud environments.
- To address limitations of existing deep learning-based IDSs, such as overfitting and unstable training.
- To enhance the reliability, interpretability, and robustness of cloud security systems.
Main Methods:
- Utilized benchmark datasets (NSL-KDD, CICIDS2017) for network traffic analysis.
- Applied data preprocessing techniques including missing value imputation and Min-Max normalization.
- Developed and implemented the TaWSA_WRN model, incorporating Taylor Wave Search Algorithm for hyperparameter optimization and feature selection.
- Employed SHAP for model-agnostic interpretability to gain insights into traffic features.
Main Results:
- Achieved high performance metrics: maximum True Negative Rate (TNR) of 96.857%, accuracy of 97.190%, and True Positive Rate (TPR) of 97.589%.
- Demonstrated improved learning stability and parameter optimization through the Taylor Wave Search Algorithm.
- Provided valuable insights into domain-relevant traffic features via SHAP interpretability.
Conclusions:
- The proposed TaWSA_WRN framework offers a reliable, interpretable, and robust solution for intrusion detection and mitigation in secure cloud computing environments.
- The response-guided mitigation strategy enhances security beyond single network-level defenses.
- The framework effectively overcomes common deep learning drawbacks in IDS development.
Related Concept Videos
02:28Leaky Scanning
During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R stands for...
01:20Discrete-Time Fourier Series
The Discrete-Time Fourier Series (DTFS) is a fundamental concept in signal processing, serving as the discrete-time counterpart to the continuous-time Fourier series. It allows for the representation and analysis of discrete-time periodic signals in terms of their frequency components. Unlike its continuous counterpart, which utilizes integrals, the calculation of DTFS expansion coefficients involves summations due to the discrete nature of the signal.
For a discrete-time periodic signal x[n]...
For a discrete-time periodic signal x[n]...