XI2S-IDS: An Explainable Intelligent 2-Stage Intrusion Detection System

Future Internet, Journal Year: 2025, Volume and Issue: 17(1), P. 25 - 25

Published: Jan. 8, 2025

The rapid evolution of technologies such as the Internet Things (IoT), 5G, and cloud computing has exponentially increased complexity cyber attacks. Modern Intrusion Detection Systems (IDSs) must be capable identifying not only frequent, well-known attacks but also low-frequency, subtle intrusions that are often missed by traditional systems. challenge is further compounded fact most IDS rely on black-box machine learning (ML) deep (DL) models, making it difficult for security teams to interpret their decisions. This lack transparency particularly problematic in environments where quick informed responses crucial. To address these challenges, we introduce XI2S-IDS framework—an Explainable, Intelligent 2-Stage System. framework uniquely combines a two-stage approach with SHAP-based explanations, offering improved detection interpretability low-frequency Binary classification conducted first stage followed multi-class second stage. By leveraging SHAP values, enhances decision-making, allowing analysts gain clear insights into feature importance model’s rationale. Experiments UNSW-NB15 CICIDS2017 datasets demonstrate significant improvements performance, notable reduction false negative rates attacks, while maintaining high precision, recall, F1-scores.

Language: Английский

---

Detection of Anomalies in Data Streams Using the LSTM-CNN Model

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1610 - 1610

Published: March 6, 2025

This paper presents a comparative analysis of selected deep learning methods applied to anomaly detection in data streams. The results obtained on the popular Yahoo! Webscope S5 dataset are used for computational experiments. two commonly and recommended models literature, which basis this analysis, following: LSTM its more complicated variant, autoencoder. Additionally, usefulness an innovative LSTM-CNN approach is evaluated. indicate that can successfully be streams as performance compares favorably with mentioned standard models. For evaluation, F1score used.

Language: Английский

---

Integrating contextual intelligence with mixture of experts for signature and anomaly-based intrusion detection in CPS security

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Language: Английский

---

HoleMal: A lightweight IoT malware detection framework based on efficient host-level traffic processing

Computers & Security, Journal Year: 2025, Volume and Issue: unknown, P. 104360 - 104360

Published: Feb. 1, 2025

Language: Английский

---

ASCDNet: development of adaptive serial cascaded deep network and improved heuristic algorithm for smart transportation planning and traffic flow prediction

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2025, Volume and Issue: unknown

Published: March 18, 2025

Language: Английский

---

eBiTCN: Efficient bidirectional temporal convolution network for encrypted malicious network traffic detection

Journal of Computer Security, Journal Year: 2025, Volume and Issue: unknown

Published: April 13, 2025

The growing prevalence of encrypted malicious network traffic poses significant challenges for cybersecurity, as it conceals the content from traditional detection methods. Temporal convolutional networks (TCNs) present promising capabilities extracting complex temporal features and patterns dynamic flow data. However, unidirectional nature TCNs limits their effectiveness in capturing full context traffic, which often exhibits bidirectional dependencies. Consequently, a few studies have proposed TCN (BiTCN) architectures to address limitations. these methods that require amount parameters be learned, imposes high memory requirements on computational resources training such models. In this study, we introduce efficient (eBiTCN) model, an BiTCN requires fewer yet not at expense cost effective detection. eBiTCN framework combines processor, lightweight gating mechanism, attention, dropout, novel loss function, dense layers. Extensive experiments show outperforms eight state-of-the-art competing models terms efficacy, speed, scalability. model showcased robust performance detecting evolving attacks excelled across various real-world datasets. Its efficiency speed reduced usage translates lower infrastructure costs, making accessible choice deployment. These findings highlight eBiTCN’s practicality dependability addressing contemporary security needs.

Language: Английский

---

Prediction of android ransomware with deep learning model using hybrid cryptography

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 27, 2024

Language: Английский

---

Survey on identification and prediction of security threats using various deep learning models on software testing

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Feb. 3, 2024

Language: Английский

---

Research on highway traffic flow prediction based on a hybrid model of ARIMA–GWO–LSTM

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 2, 2024

Language: Английский

---

A Transformer Based Malicious Traffic Detection Method in Android Mobile Networks

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 370 - 385

Published: Dec. 14, 2024

Language: Английский

---