Generating Phishing Attacks using ChatGPT
Preprint
Abstract
The ability of ChatGPT to generate human-like responses and understand context has made it a popular tool for conversational agents, content creation, data analysis, and research and innovation. However, its effectiveness and ease of accessibility makes it a prime target for generating malicious content, such as phishing attacks, that can put users at risk. In this work, we identify several malicious prompts that can be provided to ChatGPT to generate functional phishing websites. Through an iterative approach, we find that these phishing websites can be made to imitate popular brands and emulate several evasive tactics that have been known to avoid detection by anti-phishing entities. These attacks can be generated using vanilla ChatGPT without the need of any prior adversarial exploits (jailbreaking).Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Engineering Education in the Era of ChatGPT: Promise and Pitfalls of Generative AI for Education2023
- ChatGPT and Software Testing Education: Promises & Perils2023
- ChatGPT and the Future of Medical WritingRadiology, 2023
- Advanced evasion attacks and mitigations on practical ML‐based phishing website classifiersInternational Journal of Intelligent Systems, 2021
- Phishing Attacks: A Recent Comprehensive Study and a New AnatomyFrontiers in Computer Science, 2021
- Phishing Attacks Survey: Types, Vectors, and Technical ApproachesFuture Internet, 2020
- A stacking model using URL and HTML features for phishing webpage detectionFuture Generation Computer Systems, 2019
- A survey and classification of web phishing detection schemesSecurity and Communication Networks, 2016
- TrustQR: A New Technique for the Detection of Phishing Attacks on QR CodeAdvanced Science Letters, 2016