Investigate Discriminative AutoEncoder in Few-shot Learning-based Anomaly Detection DOI Open Access
Van Loi Cao

REV Journal on Electronics and Communications, Journal Year: 2024, Volume and Issue: 14(2)

Published: July 2, 2024

Discriminative AutoEncoder (DisAE) plays a crucial role in enhancing the adaptability and gener- alization of few-shot learning methods (DisAEFL) for detecting rare anomalies. DisAE captures meta- knowledge from multiple known tasks, facilitating rapid adaptation DisAEFL. Key factors like discriminative parameter (a) normal proportion (pn) significantly impact DisAEFL performance. However, their influence on manifold DisAEFL’s efficacy cyberattack detection remain understudied cybersecurity. This study presents an investigative approach to probe DisAE’s performance addressing rare, unseen cyberattacks, aiming gain insight into outline future research directions. Through intensive analysis, we focus parameters pn, detailing how examine them observe effects Two main experiments are conducted investigate influences. Experimental results NSL-KDD dataset reveal strong correlation between these both These findings suggest strategies more efficiently constructing enhance generalization. Overall, this contributes advancing anomaly methodologies cybersecurity by shedding light interplay DisAE, DisAEFL, parameters.

Language: Английский

Enhancing aviation control security through ADS-B injection detection using ensemble meta-learning models with Explainable AI DOI Creative Commons
Vajratiya Vajrobol, Geetika Jain Saxena, Sanjeev Singh

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 112, P. 63 - 73

Published: Nov. 1, 2024

Language: Английский

Citations

4
Optimized Intrusion Detection Approach for Cyber‐Physical System Using Meta‐Learning With Stacked Generalization: An Ensemble Learning Inspired Approach DOI
Ram Ji, Neerendra Kumar,

Devanand Padha

et al.

Security and Privacy, Journal Year: 2025, Volume and Issue: 8(3)

Published: April 27, 2025

ABSTRACT Cyber‐physical systems (CPSs) are crucial in providing vital infrastructure like smart grids, cities, automobiles, healthcare systems, and so forth, for many nations. CPSs vulnerable to various attacks due their large attack surface. An on these may lead the disruption of critical services. To protect an optimized intrusion detection approach is needed. Although approaches exist, they have limitations poor accuracy, high time, space time complexities, false alarm rates, etc. stack generalized meta‐learner‐based has been proposed this paper. The utilizes numerous core models a meta‐learner classify network traffic CPSs. base trained learning data, outcomes used as input features meta‐learner, which then makes final prediction. Four classifiers being models, namely random forest (RF), gradient boosting (GB), multiple layer perceptron (MLP), k ‐nearest neighbors (KNNs), extreme (XGB) classifier meta‐learner. predictions generated using stacking ensemble approach. Auto encoders feature extraction, thereby utilizing unique objective function designed recursive attribute elimination. presented selects only 10 out 46 features, helps reducing complexities. While implementing CIC‐IoT‐2023 dataset, following results obtained: multi‐classification accuracy (98.94%), precision (0.99), recall F 1 score average positive rate (0.0003), (0.12 s). When implemented NSL‐KDD (99%), (0.0012). UNSW‐NB15 (99.56%), (0.0002). performs better contrast other cutting‐edge approaches. Also, introduces novel effective strategy

Language: Английский

Citations

0
A survey: contribution of ML & DL to the detection & prevention of botnet attacks DOI
Yassine El Yamani, Youssef Baddi, Najib El Kamoun

et al.

Journal of Reliable Intelligent Environments, Journal Year: 2024, Volume and Issue: 10(4), P. 431 - 448

Published: June 24, 2024

Language: Английский

Citations

3
Improving Data Fusion for Fake News Detection: A Hybrid Fusion Approach for Unimodal and Multimodal Data DOI Creative Commons
Suhaib Kh. Hamed,

Mohd Juzaiddin Ab Aziz,

Mohd Ridzwan Yaakub

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 112412 - 112425

Published: Jan. 1, 2024

Language: Английский

Citations

3
Real-Time Microgrid Energy Scheduling Using Meta-Reinforcement Learning DOI Creative Commons
Huan Shen, Xingfa Shen, Yiming Chen

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(10), P. 2367 - 2367

Published: May 14, 2024

With the rapid development of renewable energy and increasing maturity storage technology, microgrids are quickly becoming popular worldwide. The stochastic scheduling problem can increase operational costs resource wastage. In order to reduce optimize utilization efficiency, real-time becomes particularly important. After collecting extensive data, reinforcement learning (RL) provide good strategies. However, it cannot make quick rational decisions in different environments. As a method with generalization ability, meta-learning compensate for this deficiency. Therefore, paper introduces microgrid strategy based on RL meta-learning. This adapt environments small amount training enabling policy generation early stages operation. first establishes model, including components such as storage, load, distributed (DG). Then, we use meta-reinforcement framework train initial strategy, considering various constraints microgrid. experimental results show that MAML-based has advantages improving reducing research provides new intelligent solution microgrids’ efficient, stable, economical operation their stages.

Language: Английский

Citations

1
Investigate Discriminative AutoEncoder in Few-shot Learning-based Anomaly Detection DOI Open Access
Van Loi Cao

REV Journal on Electronics and Communications, Journal Year: 2024, Volume and Issue: 14(2)

Published: July 2, 2024

Discriminative AutoEncoder (DisAE) plays a crucial role in enhancing the adaptability and gener- alization of few-shot learning methods (DisAEFL) for detecting rare anomalies. DisAE captures meta- knowledge from multiple known tasks, facilitating rapid adaptation DisAEFL. Key factors like discriminative parameter (a) normal proportion (pn) significantly impact DisAEFL performance. However, their influence on manifold DisAEFL’s efficacy cyberattack detection remain understudied cybersecurity. This study presents an investigative approach to probe DisAE’s performance addressing rare, unseen cyberattacks, aiming gain insight into outline future research directions. Through intensive analysis, we focus parameters pn, detailing how examine them observe effects Two main experiments are conducted investigate influences. Experimental results NSL-KDD dataset reveal strong correlation between these both These findings suggest strategies more efficiently constructing enhance generalization. Overall, this contributes advancing anomaly methodologies cybersecurity by shedding light interplay DisAE, DisAEFL, parameters.

Language: Английский

Citations

0