ChatPhishDetector: Detecting Phishing Sites Using Large Language Models

被引:4
作者
Koide, Takashi [1 ]
Nakano, Hiroki [2 ]
Chiba, Daiki
机构
[1] NTT Secur Holdings Corp, Tokyo 1010021, Japan
[2] NTT Corp, Tokyo 1010021, Japan
来源
IEEE ACCESS | 2024年 / 12卷
关键词
Phishing; Uniform resource locators; Large language models; Crawlers; Codes; Web pages; Security; Accuracy; Visualization; Cognition; phishing sites; social engineering;
D O I
10.1109/ACCESS.2024.3483905
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Large Language Models (LLMs), such as ChatGPT, are significantly impacting various fields. While LLMs have been extensively studied for code generation and text synthesis, their application in detecting malicious web content, particularly phishing sites, remains largely unexplored. To counter the increasing cyber-attacks that leverage LLMs for creating more sophisticated and convincing phishing content, it is crucial to automate detection by harnessing LLMs' advanced capabilities. This paper introduces ChatPhishDetector, a novel system that employs LLMs to identify phishing sites. Our approach involves using a web crawler to collect website information, generating prompts for LLMs based on the gathered data, and extracting detection results from LLM responses. This system enables accurate detection of multilingual phishing sites by identifying impersonated brands and social engineering techniques within the entire website context, without requiring machine learning model training. We evaluated our system's performance using our own dataset and compared it with baseline systems and several LLMs. Experiments using GPT-4V showed exceptional results, achieving 98.7% precision and 99.6% recall, surpassing the detection performance of other LLMs and existing systems. These findings highlight the potential of LLMs for protecting users from online fraudulent activities and provide crucial insights for strengthening defenses against phishing attacks.
引用
收藏
页码:154381 / 154400
页数:20
相关论文
共 50 条
[41]   Using Natural Language Processing for Phishing Detection [J].
Jonker, Richard Adolph Aires ;
Poudel, Roshan ;
Pedrosa, Tiago ;
Lopes, Rui Pedro .
OPTIMIZATION, LEARNING ALGORITHMS AND APPLICATIONS, OL2A 2021, 2021, 1488 :540-552
[42]   Dual Adapter Tuning of Vision-Language Models Using Large Language Models [J].
Zarei, Mohammad Reza ;
Akkasi, Abbas ;
Komeili, Majid .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2025, 18 (01)
[43]   Task Decomposition and Self-Evaluation Mechanisms for Home Healthcare Robots Using Large Language Models [J].
Liu, Liteng ;
Zhang, Sen ;
Jiang, Yangmin ;
Guo, Jingzhen ;
Zhao, Wenlong .
IEEE ACCESS, 2025, 13 :65726-65736
[44]   Watermarking for Large Language Models: A Survey [J].
Yang, Zhiguang ;
Zhao, Gejian ;
Wu, Hanzhou .
MATHEMATICS, 2025, 13 (09)
[45]   An Anchoring Effect in Large Language Models [J].
E. O'Leary, Daniel .
IEEE INTELLIGENT SYSTEMS, 2025, 40 (02) :23-26
[46]   Large Language Models and Computer Security [J].
Iyengar, Arun ;
Kundu, Ashish .
2023 5TH IEEE INTERNATIONAL CONFERENCE ON TRUST, PRIVACY AND SECURITY IN INTELLIGENT SYSTEMS AND APPLICATIONS, TPS-ISA, 2023, :307-313
[47]   Using Large Language Models to Improve Sentiment Analysis in Latvian Language [J].
Purvins, Pauls ;
Urtans, Evalds ;
Caune, Vairis .
BALTIC JOURNAL OF MODERN COMPUTING, 2024, 12 (02) :165-175
[48]   Business Process Modeling Notation-Large Language Model: Transforming Business Processing Modeling Notation Models Into Smart Contracts Using Large Language Models [J].
Gao, Sheng ;
Liu, Wenting ;
Zhu, Jianming ;
Dong, Xuewen ;
Dong, Jin .
IEEE SOFTWARE, 2025, 42 (04) :50-57
[49]   Detecting phishing attacks using a combined model of LSTM and CNN [J].
Ariyadasa, Subhash ;
Fernando, Subha ;
Fernando, Shantha .
INTERNATIONAL JOURNAL OF ADVANCED AND APPLIED SCIENCES, 2020, 7 (07) :56-67
[50]   Verbal lie detection using Large Language Models [J].
Loconte, Riccardo ;
Russo, Roberto ;
Capuozzo, Pasquale ;
Pietrini, Pietro ;
Sartori, Giuseppe .
SCIENTIFIC REPORTS, 2023, 13 (01)