[Defense] Study on Adversarial Robustness of Phishing Email Detection Models
Monday, November 21, 2022
3:00 pm - 4:00 pm
In
Partial
Fulfillment
of
the
Requirements
for
the
Master
of
Science
Parisa
Mehdi
Gholampour
will
defend
her
thesis
Study
on Adversarial
Robustness
of
Phishing
Email
Detection
Models
Abstract
Developing robust detection models against phishing emails has long been a main concerns of the cyber defence community. Currently public phishing/legitimate datasets are lack adversarial email examples which keeps the detection models vulnerable. To address this problem, we developed an augmented phishing/legitimate email dataset, utilizing different adversarial text attack techniques. In this work, the emails that can easily transform to adversarial examples and their unique characteristics have been detected and analyzed. Henceforth the models are retrained with adversarial dataset and the results show that accuracy and F1 score of the models have been improved under attack methods. In another experiment synthetic phishing emails are generated using a fine-tuned GPT-2 model. The detection model has retrained with newly formed dataset and we have observed the accuracy and robustness of the model has not improved under black box attack methods.
Monday,
November
21,
2022
3:00PM
-
4:00PM
CT
PGH
550
Dr. Rakesh M. Verma, thesis advisor
Faculty, students and the general public are invited.
