MLPhishChain: a machine learning-based blockchain framework for reducing phishing threats DOI Creative Commons
Fouad Trad,

Elie Semaan-Nasr,

Ali Chehab

et al.

Frontiers in Blockchain, Journal Year: 2024, Volume and Issue: 7

Published: Dec. 12, 2024

Introduction Phishing attacks pose a significant threat to online security by deceiving users into divulging sensitive information through fraudulent websites. Traditional anti-phishing approaches are centralized and reactive, exhibiting critical limitations such as delayed detection, poor adaptability evolving threats, susceptibility data tampering, lack of transparency. Methods This paper presents MLPhishChain, decentralized application (DApp) that integrates blockchain technology with machine learning (ML) provide proactive transparent solution for URL verification. Users can submit URLs automated phishing analysis via an ML model, each URL’s status securely recorded on immutable ledger. To address the dynamic nature MLPhishChain features re-evaluation mechanism, enabling request updated assessments website content evolve. Additionally, system incorporates from external services (e.g., VirusTotal) offer multi-source validation risk, enhancing user confidence decision-making. Results The was built using Ganache Truffle, performance metrics were computed evaluate its efficacy in terms latency, scalability, resource consumption. indicate proposed achieves rapid verification low scales effectively handle increasing submissions, optimizes usage. Discussion By leveraging strengths intelligent algorithms, addresses shortcomings traditional methods. It delivers reliable adaptable capable addressing threats. approach establishes new standard characterized enhanced transparency, resilience, adaptability.

Language: Английский

From Vulnerability to Defense: The Role of Large Language Models in Enhancing Cybersecurity DOI Creative Commons

Wafaa Kasri,

Yassine Himeur, Hamzah Ali Alkhazaleh

et al.

Computation, Journal Year: 2025, Volume and Issue: 13(2), P. 30 - 30

Published: Jan. 29, 2025

The escalating complexity of cyber threats, coupled with the rapid evolution digital landscapes, poses significant challenges to traditional cybersecurity mechanisms. This review explores transformative role LLMs in addressing critical cybersecurity. With landscapes and increasing sophistication security mechanisms often fall short detecting, mitigating, responding complex risks. LLMs, such as GPT, BERT, PaLM, demonstrate unparalleled capabilities natural language processing, enabling them parse vast datasets, identify vulnerabilities, automate threat detection. Their applications extend phishing detection, malware analysis, drafting policies, even incident response. By leveraging advanced features like context awareness real-time adaptability, enhance organizational resilience against cyberattacks while also facilitating more informed decision-making. However, deploying is not without challenges, including issues interpretability, scalability, ethical concerns, susceptibility adversarial attacks. critically examines foundational elements, real-world applications, limitations highlighting key advancements their integration into frameworks. Through detailed analysis case studies, this paper identifies emerging trends proposes future research directions, improving robustness, privacy automating management. study concludes by emphasizing potential redefine cybersecurity, driving innovation enhancing ecosystems.

Language: Английский

Citations

9
A Review of Advancements and Applications of Pre-Trained Language Models in Cybersecurity DOI
Zefang Liu

Published: April 29, 2024

In this paper, we delve into the transformative role of pre-trained language models (PLMs) in cybersecurity, offering a comprehensive examination their deployment across wide array cybersecurity tasks. Beginning with an exploration general PLMs, including advancements and emergence domain-specific tailored for provide insightful overview foundational technologies driving these developments. The core our review focuses on multifaceted applications PLMs ranging from malware vulnerability detection to more nuanced areas like log analysis, network traffic threat intelligence, among others. We also highlight recent strides application large (LLMs), showcasing growing influence enhancing measures. By charting landscape PLM pointing toward future directions, work serves as valuable resource both research community industry practitioners, underlining critical need continued innovation harnessing fortify defenses.

Language: Английский

Citations

9
Extracting Fruit Disease Knowledge from Research Papers Based on Large Language Models and Prompt Engineering DOI Creative Commons

Yunqiao Fei,

Jingchao Fan, Guomin Zhou

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(2), P. 628 - 628

Published: Jan. 10, 2025

In China, fruit tree diseases are a significant threat to the development of industry, and knowledge about is most needed professional for farmers other practitioners in industry. Research papers primary sources that represent cutting-edge progress disease research. Traditional engineering methods acquisition require extensive cumbersome preparatory work, they demand high level background information technology skills from handlers. This paper, perspective industry dissemination, aims at users such as farmers, experts, communicators, gatherers. It proposes fast, cost-effective, low-technical-barrier method extracting research paper abstracts—K-Extract, based on large language models (LLMs) prompt engineering. Under zero-shot conditions, K-Extract utilizes conversational LLMs automate extraction knowledge. The has constructed comprehensive classification system and, through series optimized questions, effectively overcomes deficiencies LLM providing factual accuracy. tests multiple available Chinese market, results show can seamlessly integrate with any model, DeepSeek model Kimi performing particularly well. experimental indicate have accuracy rate handling judgment tasks simple Q&A tasks. simple, efficient, accurate, serve convenient tool agricultural field.

Language: Английский

Citations

1
Research on Large Language Model for Coal Mine Equipment Maintenance Based on Multi-Source Text DOI Creative Commons
Xiangang Cao,

Wangtao Xu,

Jiangbin Zhao

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(7), P. 2946 - 2946

Published: March 31, 2024

The efficient management and utilization of coal mine equipment maintenance knowledge is an indispensable foundation for advancing the establishment intelligent mines. This has problems such as scattered, low sharing, insufficient management, which restricts development intelligence. For above-mentioned problems, a large language model based on multi-source text (XCoalChat) was proposed to better manage utilize existing massive maintenance. dataset ReliableCEMK-Self-Instruction constructed obtain wide diverse amount through sample generation. Aiming at illusory problem model, graph enhancement method “Coal Mine Equipment Maintenance System—Full Life Cycle—Specification” improve density. A triple-LoRA fine-tuning mechanism DPO direct preference optimization were introduced into top baseline guarantees that XCoalChat can handle multiple Q&A decision analysis tasks with limited computing power. Compared ChatGLM, Bloom, LLama, comprehensive assessment performed by experiments including dialog consulting, professional analysis. results showed achieved best response accuracy in consulting analysis; also took least reasoning time average. outperformed other mainstream models, verify effective field

Language: Английский

Citations

4
Framework for Integrating Generative AI in Developing Competencies for Accounting and Audit Professionals DOI Open Access
Ionuț Anica-Popa, Marinela Vrîncianu, Liana-Elena Anica-Popa

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(13), P. 2621 - 2621

Published: July 4, 2024

The study aims to identify the knowledge, skills and competencies required by accounting auditing (AA) professionals in context of integrating disruptive Generative Artificial Intelligence (GenAI) technologies develop a framework for GenAI capabilities into organisational systems, harnessing its potential revolutionise lifelong learning development assist day-to-day operations decision-making. Through systematic literature review, 103 papers were analysed, outline, current business ecosystem, competencies’ demand generated AI adoption and, particular, associated risks, thus contributing body knowledge underexplored research areas. Positioned at confluence accounting, GenAI, paper introduces meaningful overview areas effective data analysis, interpretation findings, risk awareness management. It emphasizes reshapes role discovering true adopting it accordingly. new LLM-based system model that can enhance through collaboration with similar systems provides an explanatory scenario illustrate applicability audit area.

Language: Английский

Citations

4
Integrating Large Language Models with Multimodal Virtual Reality Interfaces to Support Collaborative Human–Robot Construction Work DOI
Somin Park, Carol C. Menassa, Vineet R. Kamat

et al.

Journal of Computing in Civil Engineering, Journal Year: 2024, Volume and Issue: 39(1)

Published: Oct. 28, 2024

Language: Английский

Citations

4
The Dual-Edged Sword of Large Language Models in Phishing DOI

Alec Siemerink,

Slinger Jansen, Katsiaryna Labunets

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 258 - 279

Published: Jan. 1, 2025

Language: Английский

Citations

0
Intelligent ETL for Enterprise Software Applications Using Unstructured Data DOI

M. Joshi,

Vijay K. Madisetti

Journal of Software Engineering and Applications, Journal Year: 2025, Volume and Issue: 18(01), P. 44 - 65

Published: Jan. 1, 2025

Language: Английский

Citations

0
Phishing Detection Methods DOI
Sally Dafaalla Awadalkarim Abualgasim, Zeinab E. Ahmed

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 25 - 48

Published: Feb. 14, 2025

This chapter explores the evolution of phishing detection methods, present traditional, advanced, and hybrid approaches. Traditional methods provide a base layer defense, but their effectiveness is limited against adaptive attacks. Advanced techniques employ machine learning (ML) deep (DL) to enhance accuracy leveraging data-driven models that analyze URL structures, email content, website behavior. Hybrid combine multiple optimize performance. Case studies illustrate practical application these methodologies in various domains which include use convolutional neural networks (CNNs), long short-term memory (LSTMs), ensemble algorithms such as Random Forests Gradient Boosting, achieving accuracies exceeding 97% many cases. Research also highlights on large language (LLMs) Universal Adversarial Perturbation (UAP) techniques, for detecting advanced strategies. Challenges imbalanced datasets real-time requirements.

Language: Английский

Citations

0
To Ensemble or Not: Assessing Majority Voting Strategies for Phishing Detection with Large Language Models DOI
Fouad Trad, Ali Chehab

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 158 - 173

Published: Jan. 1, 2025

Language: Английский

Citations

0