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

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

---

The Convergence of Artificial Intelligence and Cybersecurity

Advances in finance, accounting, and economics book series, Journal Year: 2025, Volume and Issue: unknown, P. 321 - 350

Published: Jan. 14, 2025

Understanding the confluence of artificial intelligence (AI) and cybersecurity is important due to emerging landscape digital threats growing experience cyberattacks. According a study presented at World Economic Forum in 2024, global cost cybercrime forecasted jump $23.84 trillion by 2027. We often observe that cyberattacks' economic political impact has increased, especially large organizations, rise vulnerabilities increased value damages, with long-term effects. Organizations should be aware relationships between AI improved cybersecurity, including creative destruction two-faced on organizations. On one hand, could provide new growth opportunities enhance ways. other it adds systems determines enhanced needs for data protection general security measures.

Language: Английский

---

Perception towards the Acceptance of Digital Health Services among the People of Bangladesh

WSEAS TRANSACTIONS ON BUSINESS AND ECONOMICS, Journal Year: 2024, Volume and Issue: 21, P. 1557 - 1570

Published: July 12, 2024

The research intends to determine the influential factors of individual willingness use digital health services in Bangladesh. quantitative method was conducted obtain purposes this study. To collect primary data, a questionnaire link and direct interaction with purposive sample 300 people were used. for study made up who services. discovered that six factors, totaling 24 items, influence Bangladeshis’ acceptance reliability test variables 6 determinants is reliable because Cronbach’s alpha 0.569, which greater than standard 0.5. This positive correlation between social cultural, technological, economic, convenience, security, perceived utility using two-tailed significance level 0.01 or less. found economic advantages technology literacy understanding greatly care acceptability, statistically significant outcomes other determinant factors. Policymakers, healthcare practitioners, developers can data customize their plans solutions Bangladeshi requirements. Promoting perceptions removing barriers will increase service Bangladesh, increasing accessibility.

Language: Английский

---

Encouraging Creativity and Innovation in the Cybersecurity Culture of the Organisation for Sustainable Value and Growth

Advances in finance, accounting, and economics book series, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 28

Published: Jan. 31, 2025

Creativity and innovation are vital to combat cybercrime protect information related systems of organisations. Organisations in which creativity applied the security function experience fewer cyber breaches, manage risk more easily, greater productivity faster growth can implement latest technologies, knowing that organisation protected. However, there is limited guidance for organisations on how incorporate as part cybersecurity culture. In this chapter, determinants positively influence outlined context a A framework culture presented theoretical contribution, leveraging values derived from existing models frameworks. The with corresponding scorecard, practical be utilised by leadership encourage organisation.

Language: Английский

---

Class-Based SHAP Analysis for Improved Explainability Insights in NIDS

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 303 - 313

Published: Jan. 1, 2025

Language: Английский

---

ExpLEA-AIner: Proposition and Development of the Model-Driven Approach to Incorporating Explainable AI in Network Intrusion Detection Systems for Law Enforcement Agencies

Lecture notes in business information processing, Journal Year: 2025, Volume and Issue: unknown, P. 334 - 347

Published: Jan. 1, 2025

Language: Английский

---

Deep learning-based LDL-C level prediction and explainable AI interpretation

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 188, P. 109905 - 109905

Published: Feb. 26, 2025

Language: Английский

---

Proposition of a Novel Type of Attacks Targetting Explainable AI Algorithms in Cybersecurity

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 289 - 304

Published: Jan. 1, 2025

Language: Английский

---

AI-driven cybersecurity framework for software development based on the ANN-ISM paradigm

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 18, 2025

Abstract With the increasing reliance on software applications, cybersecurity threats have become a critical concern for developers and organizations. The answer to this vulnerability is AI systems, which help us adapt little better, as traditional measures in security failed respond upcoming threats. This paper presents an innovative framework using AI, by Artificial Neural Network (ANN)—Interpretive Structural Modeling (ISM) model, improve threat detection, assessment, risk response during development. helps realize dynamic, intelligent part of Software Development life cycle (SDLC). Initially, existing risks coding are systematically evaluated identify potential gaps integrate best practices into proposed model. In second phase, empirical survey was conducted validate findings systematic literature review (SLR). third hybrid approach employed, integrating ANN real-time detection assessment. It utilizes ISM analyze relationships between vulnerabilities, creating structured understanding interdependencies. A case study last stage test evaluate AI-driven Mitigation Model Secure Coding. multi-level categorization system also used assess maturity across five key levels: Ad hoc, Planned, Standardized, Metrics-Driven, Continuous Improvements. identifies 15 vulnerabilities coding, along with 158 mitigating these risks. areas insecure develops scalable model address different levels. results show that outperforms systems detecting weaknesses simultaneously fixing problems. During Levels 1–3 improvement process, advanced methods protect against Our analysis reveals organizations at 4 5 still need entirely shift AI-based protection tools techniques. provides managers valuable insights, enabling them select enhancements tailored their organization's development stages. supports automated analysis, helping stay vigilant introduces novel ANN-ISM modeling formalisms. By merging secure principles, research enhances connection AI-generated insights real-world usage.

Language: Английский

---

A Literature Review of Explainable Tabular Data

Published: Aug. 8, 2024

Explainable Artificial Intelligence (XAI) plays a vital role in increasing transparency and trust machine learning models, particularly when applied to tabular data which is used domains such as finance, healthcare, marketing. This paper presents an extensive survey of XAI techniques with aims analyze recent research developments since 2021. The classes describes several pertinent data, it identifies challenges specific this domain, explores potential applications emerging trends. Future directions are outlined, concentrating on the need for clear definitions terminology used, security, user-centric explanations, enhanced interaction, robust evaluation metrics, advancements adversarial example-based analysis. aim contribute evolving field XAI, provide insights effective, trustworthy, transparent decision-making using data.

Language: Английский

---