LLM-AE-MP: Web attack detection using a large language model with autoencoder and multilayer perceptron

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126982 - 126982

Опубликована: Фев. 1, 2025

Язык: Английский

---

Industrial IoT intrusion attack detection based on composite attention-driven multi-layer pyramid features

Computer Networks, Год журнала: 2025, Номер unknown, С. 111207 - 111207

Опубликована: Март 1, 2025

Язык: Английский

---

Enhancing Online Security: A Novel Machine Learning Framework for Robust Detection of Known and Unknown Malicious URLs

Journal of theoretical and applied electronic commerce research, Год журнала: 2024, Номер 19(4), С. 2919 - 2960

Опубликована: Окт. 26, 2024

The rapid expansion of the internet has led to a corresponding surge in malicious online activities, posing significant threats users and organizations. Cybercriminals exploit uniform resource locators (URLs) disseminate harmful content, execute phishing schemes, orchestrate various cyber attacks. As these evolve, detecting URLs (MURLs) become crucial for safeguarding ensuring secure environment. In response this urgent need, we propose novel machine learning-driven framework designed identify known unknown MURLs effectively. Our approach leverages comprehensive dataset encompassing labels—including benign, phishing, defacement, malware—to engineer robust set features validated through extensive statistical analyses. resulting URL detection system (MUDS) combines supervised learning techniques, tree-based algorithms, advanced data preprocessing, achieving high accuracy 96.83% MURLs. For MURLs, proposed utilizes CL_K-means, modified k-means clustering algorithm, alongside two additional biased classifiers, 92.54% on simulated zero-day datasets. With an average processing time under 14 milliseconds per instance, MUDS is optimized real-time integration into network endpoint systems. These outcomes highlight efficacy efficiency fortifying security by identifying mitigating thereby reinforcing digital landscape against threats.

Язык: Английский

---

Biologically inspired oscillating activation functions can bridge the performance gap between biological and artificial neurons

Expert Systems with Applications, Год журнала: 2024, Номер unknown, С. 126036 - 126036

Опубликована: Дек. 1, 2024

Язык: Английский

---

Enhanced Web Security Using Cross-Feature Analysis of Visual Design, Live Logs and Code Structures

2022 7th International Conference on Communication and Electronics Systems (ICCES), Год журнала: 2024, Номер unknown, С. 860 - 866

Опубликована: Дек. 16, 2024

Язык: Английский

---