Pristine and Malicious URLs

The goal of our research is to identify malicious advertisement URLs and apply adversarial attacks on ensembles. We extract lexical and web-scrapped features using Python code. Then 4 machine learning algorithms are applied for the classification process, and then K-means clustering for the visual understanding. We check the vulnerability of the models by the adversarial examples. We applied a Zeroth Order optimization adversarial attack to the models and computed the attack accuracy.

Datasets are taken from different sources available on the internet. We have considered 12 different datasets, which consist of 6 malicious and 6 benign URLs. The dataset includes about 3980870 URLs. We extracted the 89 lexical and web-scraped features for the further task.

Dataset is for the paper:
E. Nowroozi, Abhishek, M. Mohammadi and M. Conti, "An Adversarial Attack Analysis on Malicious Advertisement URL Detection Framework," in IEEE Transactions on Network and Service Management, vol. 20, no. 2, pp. 1332-1344, June 2023, doi: 10.1109/TNSM.2022.3225217.