CoChat
Sign Up
Cited by 39Network Security and Intrusion DetectionInternet Traffic Analysis and Secure E-votingNetwork Packet Processing and Optimization

Enhancing Cybersecurity: The Development of a Flexible Deep Learning Model for Enhanced Anomaly Detection

Gonaygunta, Hari, Nadella, Geeta Sandeep, Pramod Pawar, Priyanka, Kumar, Deepak·2024·2024 Systems and Information Engineering Design Symposium (SIEDS)
DOI 10.1109/sieds61124.2024.10534661
Open this paper in CoChat — free account

Abstract

Using expert systems and relevant machine learning methods, automating network intrusion detection has become commonplace. However, the interconnectedness of many industrial control systems and the Internet of Things (IoT) has made cyber attacks on critical infrastructure communication networks a significant concern. These Critical Cyber-Physical Systems (CPSs) experience massive network traffic, posing a challenge for conventional machine-learning techniques to identify anomalies. This paper introduces a novel approach that overcomes these limitations, leveraging the power of deep learning to detect and classify anomalies with remarkable accuracy. By utilizing deep models like Deep Neural Network (DNN) and Deep Short-Term Memory (LSTM) in a two-stage procedure, we significantly enhance the capabilities of our proposed methodology. We also employ a Deep Sparse Autoencoder (DSAE) to resolve the feature engineering problem and prepare data for processing. The effectiveness of this strategy is evaluated using datasets collected from the IoT ecosystem, specifically IoT-23 and LITNET-2020. The evaluation results for the proposed method are presented and discussed, comparing its statistical significance with the most cutting-edge techniques for detecting network anomalies.

Integrity signals

Registry

Crossref · 10.1109/sieds61124.2024.10534661

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Gonaygunta et al. [35] proposed a flexible deep-learning-based anomaly detection model employing a stacked ensemble architecture using the IoT-23 and LITNET-2020 network traffic datasets.

    “Using the IoT-23 and LITNET-2020 network traffic datasets, Gonaygunta et al. [35] proposed a flexible deep-learning-based anomaly detection model employing a stacked ensemble architecture.”

    From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [35]

  • Time-series dependency-based anomaly detection on network traffic is particularly effective for attacks that explicitly disturb temporal patterns of communication, such as DoS/DDoS, flooding, scanning/probing, and botnet-driven bursts, where anomalies manifest as abrupt changes in flow-arrival rates, inter-arrival times, and session durations.

    “First, this data type is particularly effective for attacks that explicitly disturb temporal patterns of communication, such as DoS/DDoS, flooding, scanning/probing, and botnet-driven bursts, where anomalies manifest as abrupt changes in flow-arrival rates, inter-arrival times, and session durations [35,38,40,44,45].”

    From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [35]

  • Gonaygunta et al.'s model uses a Deep Sparse Autoencoder to denoise and extract low-dimensional representations from high-dimensional NetFlow features, then a DNN and an LSTM as first-stage base classifiers, with predictions fused by a logistic regression meta-classifier.

    “A Deep Sparse Autoencoder (DSAE) denoises and extracts lowdimensional representations from high-dimensional NetFlow features. Then, a DNN and an LSTM serve as first-stage base classifiers, capturing both static nonlinear patterns and temporal dependencies in flow sequences. Their predictions are fused by a logistic regression meta-classifier to determine the final 'normal/anomalous' label.”

    From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [35]

  • Supervised sequence classifiers and hybrid ensemble models dominate the time-series literature and typically report very high accuracy and F1-scores when sufficient labeled attack data are available.

    “Finally, with respect to detection paradigms, supervised sequence classifiers and hybrid ensemble models dominate the literature and typically report very high accuracy and F1-scores when sufficient labeled attack data are available [35,39,40,45].”

    From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [35]

  • Deep sequence models (LSTM, BLSTM-GRU, CNN + Bi-GRU) and generative architectures (FID-GAN, VAE-based digital twins) are able to exploit complex temporal patterns and achieve strong detection or classification performance on benchmark datasets.

    “Third, in terms of model behavior and failure modes, the surveyed work shows that deep sequence models (LSTM, BLSTM-GRU, CNN + Bi-GRU) and generative architectures (FID-GAN, VAE-based digital twins) are able to exploit complex temporal patterns and achieve strong detection or classification performance on benchmark datasets [35,38-40,42,44,45].”

    From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [35]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Gonaygunta, H., Nadella, G. S., Pramod Pawar, P., & Kumar, D.
Affiliations
  • University of the Cumberlands (US)
  • University of the Cumberlands
ORCID
Venue
2024 Systems and Information Engineering Design Symposium (SIEDS)
Publisher
IEEE
Published
2024-05-03
Pages
79-84
DOI
10.1109/sieds61124.2024.10534661
OpenAlex
W4398163940
Cited by
39
References
40
Citations by year
2026: 7 · 2025: 17 · 2024: 15
FWCI
17.07
Type
conference paper
Language
en
Open access
closed
Licence
Locations
Systems and Information Engineering Design Symposium (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
  • Physical Sciences › Computer Science › Hardware and Architecture › Network Packet Processing and Optimization
Keywords
network anomaly detection, network intrusion detection, cyber-physical systems, Internet of Things security, critical infrastructure, deep neural network, LSTM, deep sparse autoencoder, feature extraction, IoT-23 dataset

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review