Benchmarking the Robustness of Phishing Email Detection Systems
In Plain Terms
Companies increasingly rely on AI to catch phishing emails, but attackers can fool these systems by making tiny tweaks to the text. This study systematically tests popular AI phishing detectors against such manipulations and shows they are often easily evaded, arguing for layered defenses and offering a benchmark organizations can use to stress-test their own tools.
Artifacts
Related Papers
Cite this
APA Ampel, B. M., Gao, Y., Hu, J., Samtani, S., & Chen, H. (2023). Benchmarking the Robustness of Phishing Email Detection Systems. In Proceedings of the 29th Americas Conference on Information Systems (AMCIS).
BibTeX
@inproceedings{ampel2023benchmarking,
title={Benchmarking the Robustness of Phishing Email Detection Systems},
author={Benjamin M. Ampel and Yang Gao and James Hu and Sagar Samtani and Hsinchun Chen},
booktitle={Proceedings of the 29th Americas Conference on Information Systems (AMCIS)},
year={2023}
}
Benjamin M. Ampel
Assistant Professor in Computer Information Systems and Director, Center for CyberAI Research (CCAIR)
My research focuses on AI-enabled Cybersecurity, including Cyber Threat Intelligence, Large Language Models, and Phishing Detection.