Phishpedia A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages

Paper • Website • Video • Dataset • Citation

• This is the official implementation of "Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages" USENIX'21 link to paper, link to our website, link to our dataset.

• Existing reference-based phishing detectors:

  • :x: Lack of interpretability, only give binary decision (legit or phish)
  • :x: Not robust against distribution shift, because the classifier is biased towards the phishing training set
  • :x: Lack of a large-scale phishing benchmark dataset

• The contributions of our paper:

  • :white_check_mark: We propose a phishing identification system Phishpedia, which has high identification accuracy and low runtime overhead, outperforming the relevant state-of-the-art identification approaches.
  • :white_check_mark: We are the first to propose to use consistency-based method for phishing detection, in place of the traditional classification-based method. We investigate the consistency between the webpage domain and its brand intention. The detected brand intention provides a visual explanation for phishing decision.
  • :white_check_mark: Phishpedia is NOT trained on any phishing dataset, addressing the potential test-time distribution shift problem.
  • :white_check_mark: We release a 30k phishing benchmark dataset, each website is annotated with its URL, HTML, screenshot, and target brand: https://drive.google.com/file/d/12ypEMPRQ43zGRqHGut0Esq2z5en0DH4g/view?usp=drive_link.
  • :white_check_mark: We set up a phishing monitoring system, investigating emerging domains fed from CertStream, and we have discovered 1,704 real phishing, out of which 1133 are zero-days not reported by industrial antivirus engine (Virustotal).

Framework

Input: A URL and its screenshot Output: Phish/Benign, Phishing target

• Step 1: Enter Deep Object Detection Model, get predicted logos and inputs (inputs are not used for later prediction, just for explanation)

• Step 2: Enter Deep Siamese Model

  • If Siamese report no target, Return Benign, None
  • Else Siamese report a target, Return Phish, Phishing target

Setup

Prerequisite: Pixi installed

For Linux/Mac,

export KMP_DUPLICATE_LIB_OK=TRUE
git clone https://github.com/lindsey98/Phishpedia.git
cd Phishpedia
pixi install
chmod +x setup.sh
./setup.sh

For Windows, in PowerShell,

git clone https://github.com/lindsey98/Phishpedia.git
cd Phishpedia
pixi install
setup.bat

Running Phishpedia from Command Line

pixi run python phishpedia.py --folder <folder you want to test e.g. ./datasets/test_sites>

The testing folder should be in the structure of:

test_site_1
|__ info.txt (Write the URL)
|__ shot.png (Save the screenshot)
test_site_2
|__ info.txt (Write the URL)
|__ shot.png (Save the screenshot)
......

Running Phishpedia as a GUI tool (web-browser-based)

See WEBtool/

Install Phishpedia as a Chrome plugin

See Plugin_for_Chrome/

Project structure

- models/
|___ rcnn_bet365.pth
|___ faster_rcnn.yaml
|___ resnetv2_rgb_new.pth.tar
|___ expand_targetlist/
  |___ Adobe/
  |___ Amazon/
  |___ ......
|___ domain_map.pkl
- logo_recog.py: Deep Object Detection Model
- logo_matching.py: Deep Siamese Model
- configs.yaml: Configuration file
- phishpedia.py: Main script

Miscellaneous

• In our paper, we also implement several phishing detection and identification baselines, see here
• The logo targetlist described in our paper includes 181 brands, we have further expanded the targetlist to include 277 brands in this code repository
• For the phish discovery experiment, we obtain feed from Certstream phish_catcher, we lower the score threshold to be 40 to process more suspicious websites, readers can refer to their repo for details
• We use Scrapy for website crawling

Citation

If you find our work useful in your research, please consider citing our paper by:

@inproceedings{lin2021phishpedia,
  title={Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages},
  author={Lin, Yun and Liu, Ruofan and Divakaran, Dinil Mon and Ng, Jun Yang and Chan, Qing Zhou and Lu, Yiwen and Si, Yuxuan and Zhang, Fan and Dong, Jin Song},
  booktitle={30th $\{$USENIX$\}$ Security Symposium ($\{$USENIX$\}$ Security 21)},
  year={2021}
}

Contacts

If you have any issues running our code, you can raise an issue or send an email to [email protected], [email protected], and [email protected]