Implementation for our WWW'23 paper below:

@inproceedings{wang2023attacking,
  title={Attacking Fake News Detectors via Manipulating News Social Engagement},
  author={Wang, Haoran and Dou, Yingtong and Chen, Canyu and Sun, Lichao and Yu, Philip S and Shu, Kai},
  booktitle={Proceedings of the ACM Web Conference 2023},
  year={2023}
}

To run the code, you need FakeNewsNet dataset. Due to Twitter privacy concerns, we cannot release user Tweet data. Please send email with the title MARL Dataset Request to [email protected] to download the file with user raw Tweet data. You can unzip the dataset file under the root directory of the project.

cd MARL

To run the two random baselines:

python attack_base.py

To run MARL:

python attack.py