Network security based combined CNN-RNN models for IoT intrusion detection system

Peer-to-Peer Networking and Applications, Год журнала: 2025, Номер 18(3)

Опубликована: Март 26, 2025

Язык: Английский

---

Android Malware Detection Using Support Vector Regression for Dynamic Feature Analysis

Information, Год журнала: 2024, Номер 15(10), С. 658 - 658

Опубликована: Окт. 19, 2024

Mobile devices face significant security challenges due to the increasing proliferation of Android malware. This study introduces an innovative approach malware detection, combining Support Vector Regression (SVR) and dynamic feature analysis address escalating mobile challenges. Our research aimed develop a more accurate reliable detection system capable identifying both known novel variants. We implemented comprehensive methodology encompassing extraction from applications, preprocessing normalization, application SVR with Radial Basis Function (RBF) kernel for classification. results demonstrate SVR-based model’s superior performance, achieving 95.74% accuracy, 94.76% precision, 98.06% recall, 96.38% F1-score, outperforming benchmark algorithms including SVM, Random Forest, CNN. The model exhibited excellent discriminative ability Area Under Curve (AUC) 0.98 in ROC analysis. proposed capacity capture complex, non-linear relationships space significantly enhanced its effectiveness distinguishing between benign malicious applications. provides robust foundation advancing systems, offering valuable insights researchers practitioners addressing evolving

Язык: Английский

---

FABLDroid: Malware detection based on hybrid analysis with factor analysis and broad learning methods for android applications

Engineering Science and Technology an International Journal, Год журнала: 2025, Номер 62, С. 101945 - 101945

Опубликована: Янв. 10, 2025

Язык: Английский

---

An Intelligent Technique for Android Malware Identification Using Fuzzy Rank-Based Fusion

Technologies, Год журнала: 2025, Номер 13(2), С. 45 - 45

Опубликована: Янв. 23, 2025

Android’s open-source nature, combined with its large market share, has made it a primary target for malware developers. Consequently, there is dramatic need effective Android detection methods. This paper suggests novel fuzzy rank-based fusion approach (ANDFRF). The suggested ANDFRF primarily consists of two steps: in the first step, five machine learning algorithms, comprising K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), XGbooost (XGB) and Light Gradient Boosting (LightGBM), were utilized as base classifiers initial identification Apps either goodware or apps. Second, was employed to adaptively integrate classification results obtained from algorithms. By leveraging rankings instead explicit class labels, proposed method reduces impact anomalies noisy predictions, leading more accurate ensemble outcomes. Furthermore, reflect relative importance acceptance each across multiple classifiers, providing deeper insights into ensemble’s decision-making process. framework validated on publicly accessible datasets, CICAndMal2020 DREBIN, 5-fold cross-validation technique. achieves accuracy 95.51% an AUC 95.40% DREBIN dataset. On LBC dataset, attains 95.31% 95.30%. Experimental demonstrate that scheme both efficient detection.

Язык: Английский

---

An Advanced Ensemble Framework for defending against obfuscated Windows, Android, and IoT malware

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 112908 - 112908

Опубликована: Март 1, 2025

Язык: Английский

---

An Improved Static Analysis Approach for Malware Detection by Optimizing Feature Extraction Combining Different ML Algorithms

Communications in computer and information science, Год журнала: 2025, Номер unknown, С. 102 - 115

Опубликована: Янв. 1, 2025

Язык: Английский

---

Comprehensive review on machine learning and deep learning techniques for malware detection in android and IoT devices

International Journal of Information Security, Год журнала: 2025, Номер 24(3)

Опубликована: Апрель 9, 2025

Язык: Английский

---

AI-Driven Security Systems and Intelligence Threat Response Using Autonomous Cyber Defense

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 35 - 78

Опубликована: Апрель 23, 2025

The expanding cyber threat landscape has compelled organizations to adopt AI-driven security systems for robust defense against sophisticated attacks. This chapter explores artificial intelligence in cybersecurity, emphasizing its role intelligent detection, analysis, and response. AI models, including supervised unsupervised learning, deep reinforcement have redefined cybersecurity by enabling behavior-based anomaly detection automated mitigation. Key discussions highlight autonomous making real-time decisions, leveraging adaptive control loops, employing self-healing mechanisms resilience. also examines challenges operational scalability, ethical implications of automation, the necessity human oversight decision-making. findings underscore need synergy between automation expertise foster an intelligent, ecosystem.

Язык: Английский

---

A Strategic Approach to Cyberattacks and Risk Management

IGI Global eBooks, Год журнала: 2025, Номер unknown, С. 31 - 52

Опубликована: Май 14, 2025

Cybersecurity has become an extremely important issue that companies need to focus on guarantee the safety of their information systems. As for digitalization increases, every organization must combat ever-evolving cyberattacks. By giving a succinct summary current state cyber threats, this study seeks explore relationship between cybersecurity risk management and The also highlights how crucial thorough assessment is as first step in determining vulnerabilities, assessing possible consequences attacks, setting security action priorities. Next, five key functions NIST Risk Management Framework were analyzed offer strategic perspective manage throughout business. emphasizes necessity cybersecurity, stressing incorporation into broader organizational strategy better predict prevent

Язык: Английский

---

We need to aim at the top: Factors associated with cybersecurity awareness of cyber and information security decision-makers

PLoS ONE, Год журнала: 2024, Номер 19(10), С. e0312266 - e0312266

Опубликована: Окт. 18, 2024

Cyberattacks pose a significant business risk to organizations. Although there is ample literature focusing on why people major organizational cybersecurity and how deal with it, surprisingly little we know about cyber information security decision-makers who are essentially the in charge of setting up maintaining cybersecurity. In this paper, study awareness decision-makers, investigate factors associated it. We conducted an online survey among Slovenian ( N = 283) (1) determine whether their adoption antimalware solutions organizations, (2) explore which personal characteristics awareness. Our findings indicate that well-known threats seems be quite low for individuals decision-making roles. They also provide insights into (e.g., distributed denial-of-service (DDoS) attacks, botnets, industrial espionage, phishing) operation center (SOC), advanced endpoint detection response (EDR)/extended (XDR) capabilities, critical infrastructure access control, centralized device management, multi-factor authentication, management software updates, remote data deletion lost or stolen devices) least aware of. uncovered certain positively either EDR/XDR capabilities SOC. Additionally, identified (organizational role type) (gender, age, experience technology (IT)) related decision-makers. Organization size formal education were not significant. These results offer can leveraged targeted training tailored needs groups based these key factors.

Язык: Английский

---