The DOI matches its Crossref record; the references it cites are not checked yet.
Design of deep learning models for the identifications of harmful attack activities in IIOT
Abstract
IICSs, which connect technical systems with physical systems to deliver services to businesses, have become a new field of study since they are susceptible to various cyber attacks that could compromise their ability to continue supply services to businesses. Potential risks result in lost revenue, and reputational risk for businesses. It is challenging to collect information for use in constructing a smart NIDS that can successfully recognize both current and novel assaults, despite the fact that Network Intrusion Detection Systems (NIDSs) have been recommended as a way of protection from them. This paper presents an anomalies recognition system for IICSs using DL algorithms that may train and evaluate data obtained from TCP/IP package in order to address this problem. A well network datasets NSL-KDD & UNSW-NB15 are used to assess the training courses for deep auto-encoder and deep feed-forward (FF) NN designs. The research findings result that this methodology could be used in actual IICS situations because it has a lower false positive rate & a greater detection accuracy compared to previous methods.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
Hybrid designs that combine unsupervised feature learning with supervised classification or active learning frequently achieve a favorable balance between detection rate, label efficiency, and robustness.
“Hybrid designs that combine unsupervised feature learning with supervised classification or active learning frequently achieve a favorable balance between detection rate, label efficiency, and robustness [17,23,25,29,34].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [17]
Supervised statistical classifiers tend to achieve high accuracy when ample labeled attack data are available, whereas unsupervised and semi-supervised methods offer better robustness to previously unseen or zero-day attacks at the expense of slightly lower nominal accuracy.
“Supervised statistical classifiers tend to achieve high accuracy when ample labeled attack data are available [13,15,17,20,23,25,32,34], whereas unsupervised and semi-supervised methods offer better robustness to previously unseen or zero-day attacks at the expense of slightly lower nominal accuracy [17,20,21,25,28,34].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [17]
Classical machine-learning classifiers often perform competitively on high-dimensional statistical feature spaces derived from NSL-KDD, UNSW-NB15, NF-BoT-IoT, IoT-23, and similar benchmarks.
“Third, in terms of model behavior, the comparison across studies indicates that classical machine-learning classifiers often perform competitively on high-dimensional statistical feature spaces derived from NSL-KDD, UNSW-NB15, NF-BoT-IoT, IoT-23, and similar benchmarks [17,20,23,28,32,34].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [17]
Deep architectures such as DAE, DAGMM, GCNN, and LSTM-based hybrids are mainly beneficial when modeling nonlinear feature interactions or temporal dependencies, but they can be sensitive to preprocessing choices and class imbalance, sometimes exhibiting complementary false-positive/false-negative patterns compared with simpler models.
“Deep architectures such as DAE, DAGMM, GCNN, and LSTM-based hybrids are mainly beneficial when modeling nonlinear feature interactions or temporal dependencies [13,15,17,21,23,29], but they can be sensitive to preprocessing choices and class imbalance, sometimes exhibiting complementary false-positive/falsenegative patterns compared with simpler models [20,21,28].”
From AI-Based Anomaly Detection in Industrial Control and Cyber–Physical Systems: A Data-Type-Oriented Systematic Review (2025) · cites this paper as [17]
Citations
The citation lists haven’t been fetched yet
References 9 · Cited by 15
Research works printed but not linked: 4
- Sherasiya, 2016, A survey: intrusion detection system for internet of things, J. Comput Sci Eng, 5, 91
- Abraham, 2007, Evolutionary design of intrusion detection, Int J Netw Secur, 328
- Kumar, 2012, Advanced DSP Technique to Remove Baseline Noise from ECG Signal, Int J Electron Comput Sci Eng, 1, 1013
- Kumar, 2020, Modeling and Simulation of Hybrid System, IJAST, 29, 2857
Metadata
- Authors
- RajBalaji, S., Raman, R., Pant, B., Rathour, N., Rajagopa, B. R., & Prasad, C. R.
- Affiliations
- Rathinam College of Arts & Science (IN)
- Symbiosis International University (IN)
- Graphic Era Hill University (IN)
- Uttaranchal University (IN)
- Cognizant Technology Solutions,Chennai,Tamilnadu,India
- Koneru Lakshmaiah Education Foundation (IN)
- Venue
- 2023 International Conference on Artificial Intelligence and Smart Communication (AISC)
- Publisher
- IEEE
- Published
- 2023-01-27
- Pages
- 609-613
- OpenAlex
- W4362496860
- Cited by
- 15
- References
- 9
- Citations by year
- 2026: 1 · 2025: 11 · 2024: 3
- FWCI
- 4.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Artificial Intelligence and Smart Communication (AISC) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Hardware and Architecture › Network Packet Processing and Optimization
- Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
- Keywords
- Industrial Internet of Things, intrusion detection, network intrusion detection systems, anomaly detection, deep autoencoder, deep feedforward neural network, TCP/IP traffic, cyberattacks, NSL-KDD dataset, UNSW-NB15, false positive rate
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
