Comprehensive Review of Advanced Machine Learning Techniques for Detecting and Mitigating Zero-Day Exploits DOI Creative Commons
Nachaat Mohamed, Hamed Taherdoost, Mitra Madanchian

et al.

ICST Transactions on Scalable Information Systems, Journal Year: 2024, Volume and Issue: 11

Published: June 26, 2024

This paper provides an in-depth examination of the latest machine learning (ML) methodologies applied to detection and mitigation zero-day exploits, which represent a critical vulnerability in cybersecurity. We discuss evolution techniques from basic statistical models sophisticated deep frameworks evaluate their effectiveness identifying addressing threats. The integration ML with other cybersecurity mechanisms develop adaptive, robust defense systems is also explored, alongside challenges such as data scarcity, false positives, constant arms race against cyber attackers. Special attention given innovative strategies that enhance real-time response prediction capabilities. review aims synthesize current trends anticipate future developments technologies better equip researchers, professionals, policymakers ongoing battle exploits.

Language: Английский

Revolutionizing Cybersecurity: Unleashing the Power of Artificial Intelligence and Machine Learning for Next-Generation Threat Detection DOI Open Access

Ashok Manoharan,

Mithun Sarker

International Research Journal of Modernization in Engineering Technology and Science, Journal Year: 2024, Volume and Issue: unknown

Published: March 17, 2024

Cybersecurity is a critical concern in the digital landscape.AI and ML offer hope by revolutionizing threat detection.With these technologies, organizations can spot anomalies, analyze behavioral patterns, predict potential threats.We extract valuable intelligence with Natural Language Processing, unravel complex patterns deep learning neural networks, automate detection response.There are challenges, including ethical considerations data privacy.However, AI have undeniable impact effectiveness, as shown real-world case studies.Future trends include cutting-edge advancements AI/ML for quantum computing.Embracing of cybersecurity essential staying ahead cyber threats safeguarding our assets world.

Language: Английский

Citations

36
Advancing cybersecurity: a comprehensive review of AI-driven detection techniques DOI Creative Commons

A Salem,

Safaa M. Azzam,

O. E. Emam

et al.

Journal Of Big Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Aug. 4, 2024

Abstract As the number and cleverness of cyber-attacks keep increasing rapidly, it's more important than ever to have good ways detect prevent them. Recognizing cyber threats quickly accurately is crucial because they can cause severe damage individuals businesses. This paper takes a close look at how we use artificial intelligence (AI), including machine learning (ML) deep (DL), alongside metaheuristic algorithms better. We've thoroughly examined over sixty recent studies measure effective these AI tools are identifying fighting wide range threats. Our research includes diverse array cyberattacks such as malware attacks, network intrusions, spam, others, showing that ML DL methods, together with algorithms, significantly improve well find respond We compare methods out what they're where could improve, especially face new changing cyber-attacks. presents straightforward framework for assessing Methods in threat detection. Given complexity threats, enhancing regularly ensuring strong protection critical. evaluate effectiveness limitations current proposed models, addition algorithms. vital guiding future enhancements. We're pushing smart flexible solutions adapt challenges. The findings from our suggest protecting against will rely on continuously updating stay ahead hackers' latest tricks.

Language: Английский

Citations

32
The integration of artificial intelligence in cybersecurity measures for sustainable finance platforms: An analysis DOI Creative Commons

Ezekiel Onyekachukwu Udeh,

Prisca Amajuoyi,

Kudirat Bukola Adeusi

et al.

Computer Science & IT Research Journal, Journal Year: 2024, Volume and Issue: 5(6), P. 1221 - 1246

Published: June 7, 2024

This study delves into the integration of Artificial Intelligence (AI) in cybersecurity measures within smart cities, aiming to uncover both challenges and opportunities this fusion presents. With burgeoning reliance on interconnected digital infrastructures vast data ecosystems urban environments, cities are increasingly susceptible sophisticated cyber threats. Through a systematic literature review content analysis, research identifies unique vulnerabilities faced by evaluates how AI technologies can fortify frameworks. The methodology encompasses comprehensive recent scholarly articles, industry reports, case studies assess role enhancing threat detection, response, prevention mechanisms. Key findings reveal that AI-driven solutions significantly enhance resilience against threats providing advanced analytical capabilities real-time intelligence. However, also highlights critical need for robust ethical privacy considerations deployment technologies. Strategic recommendations provided policymakers, planners, technology leaders, emphasizing importance integrating secure AI-enabled infrastructure fostering public-private partnerships. concludes with suggestions future directions, focusing implications development scalable diverse contexts. Keywords: Intelligence, Cybersecurity, Smart Cities, Urban Resilience.

Language: Английский

Citations

26
The Role of Artificial Intelligence Technology in Predictive Risk Assessment for Business Continuity: A Case Study of Greece DOI Creative Commons
Stavros Kalogiannidis, Dimitrios Kalfas, Olympia Papaevangelou

et al.

Risks, Journal Year: 2024, Volume and Issue: 12(2), P. 19 - 19

Published: Jan. 23, 2024

This study examined the efficacy of artificial intelligence (AI) technologies in predictive risk assessment and their contribution to ensuring business continuity. research aimed understand how different AI components, such as natural language processing (NLP), AI-powered data analytics, AI-driven maintenance, integration incident response planning, enhance support continuity an environment where businesses face a myriad risks, including disasters, cyberattacks, economic fluctuations. A cross-sectional design quantitative method were used collect for this from sample 360 technology specialists. The results show that have major impact on assessment. Notably, it was discovered NLP improved accuracy speed procedures. into plans particularly effective, greatly decreasing company interruptions improving recovery unforeseen events. It is advised invest skills, fields automated assessment, analytics prompt detection, maintenance operational effectiveness, AI-enhanced planning crisis management.

Language: Английский

Citations

17
AI-driven fusion with cybersecurity: Exploring current trends, advanced techniques, future directions, and policy implications for evolving paradigms– A comprehensive review DOI
Sijjad Ali, Jia Wang,

Victor Chung Ming Leung

et al.

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 102922 - 102922

Published: Jan. 1, 2025

Language: Английский

Citations

2
Enhancing Cybersecurity through AI and ML: Strategies, Challenges, and Future Directions DOI Open Access
Maryam Roshanaei,

Mahir R. Khan,

Natalie N. Sylvester

et al.

Journal of Information Security, Journal Year: 2024, Volume and Issue: 15(03), P. 320 - 339

Published: Jan. 1, 2024

The landscape of cybersecurity is rapidly evolving due to the advancement and integration Artificial Intelligence (AI) Machine Learning (ML). This paper explores crucial role AI ML in enhancing defenses against increasingly sophisticated cyber threats, while also highlighting new vulnerabilities introduced by these technologies. Through a comprehensive analysis that includes historical trends, technological evaluations, predictive modeling, dual-edged nature examined. Significant challenges such as data privacy, continuous training models, manipulation risks, ethical concerns are addressed. emphasizes balanced approach leverages innovation alongside rigorous standards robust practices. facilitates collaboration among various stakeholders develop guidelines ensure responsible effective use cybersecurity, aiming enhance system integrity privacy without compromising security.

Language: Английский

Citations

13
Comprehensive evaluation of Mal-API-2019 dataset by machine learning in malware detection DOI Creative Commons
Zhenglin Li,

Haibei Zhu,

Houze Liu

et al.

International Journal of Computer Science and Information Technology, Journal Year: 2024, Volume and Issue: 2(1), P. 1 - 9

Published: March 4, 2024

This study conducts a thorough examination of malware detection using machine learning techniques, focusing on the evaluation various classification models Mal-API-2019 dataset. The aim is to advance cybersecurity capabilities by identifying and mitigating threats more effectively. Both ensemble non-ensemble methods, such as Random Forest, XGBoost, K Nearest Neighbor (KNN), Neural Networks, are explored. Special emphasis placed importance data pre-processing particularly TF-IDF representation Principal Component Analysis, in improving model performance. Results indicate that Forest exhibit superior accuracy, precision, recall compared others, highlighting their effectiveness detection. paper also discusses limitations potential future directions, emphasizing need for continuous adaptation address evolving nature malware. research contributes ongoing discussions provides practical insights developing robust systems digital era.

Language: Английский

Citations

11
Ethical Considerations in AI-Based Cybersecurity DOI
Keshav Kaushik,

Aadil Khan,

Ankita Kumari

et al.

Blockchain technologies, Journal Year: 2024, Volume and Issue: unknown, P. 437 - 470

Published: Jan. 1, 2024

Language: Английский

Citations

8
Deep learning-based authentication for insider threat detection in critical infrastructure DOI Creative Commons
Arnoldas Budžys, Olga Kurasova, Viktor Medvedev

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(10)

Published: Aug. 29, 2024

In today's cyber environment, threats such as data breaches, cyberattacks, and unauthorized access threaten national security, critical infrastructure, financial stability. This research addresses the challenging task of protecting infrastructure from insider because high level trust these individuals typically receive. Insiders may obtain a system administrator's password through close observation or by deploying software to gather information. To solve this issue, an innovative artificial intelligence-based methodology is proposed identify user their password's keystroke dynamics. paper also introduces new Gabor Filter Matrix Transformation method transform numerical values into images revealing behavioral pattern typing. A siamese neural network (SNN) with branches convolutional networks utilized for image comparison, aiming detect attempts systems. The analyzes unique features user's timestamps transformed compares them previously submitted passwords. obtained results indicate that transforming dynamics training SNN leads lower equal error rate (EER) higher authentication accuracy than those reported in other studies. validated on publicly available collections, CMU GREYC-NISLAB datasets, which collectively comprise over 30,000 samples. It achieves lowest EER value 0.04545 compared state-of-the-art methods non-image images. concludes discussion findings potential future directions.

Language: Английский

Citations

5
Explainable deep learning approach for advanced persistent threats (APTs) detection in cybersecurity: a review DOI Creative Commons

Noor Hazlina Abdul Mutalib,

Aznul Qalid Md Sabri, Ainuddin Wahid Abdul Wahab

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(11)

Published: Sept. 18, 2024

Abstract In recent years, Advanced Persistent Threat (APT) attacks on network systems have increased through sophisticated fraud tactics. Traditional Intrusion Detection Systems (IDSs) suffer from low detection accuracy, high false-positive rates, and difficulty identifying unknown such as remote-to-local (R2L) user-to-root (U2R) attacks. This paper addresses these challenges by providing a foundational discussion of APTs the limitations existing methods. It then pivots to explore novel integration deep learning techniques Explainable Artificial Intelligence (XAI) improve APT detection. aims fill gaps in current research thorough analysis how XAI methods, Shapley Additive Explanations (SHAP) Local Interpretable Model-agnostic (LIME), can make black-box models more transparent interpretable. The objective is demonstrate necessity explainability propose solutions that enhance trustworthiness effectiveness models. offers critical approaches, highlights their strengths limitations, identifies open issues require further research. also suggests future directions combat evolving threats, paving way for effective reliable cybersecurity solutions. Overall, this emphasizes importance enhancing performance systems.

Language: Английский

Citations

5