Abstract
Fake reviews are having a devastating negative influence on online shopping sites. The proliferation of fake reviews is exacerbated by the presence of SockFarms, companies that create and operate huge sets of 'sockpuppet' accounts to promote their customers' products by posting fake reviews. Our proposed SockAttack algorithm allows such companies to optimize their actions to maximize profits. We show that SockAttack compromises the F1-score of four well-known review fraud detection engines on real-world datasets (up to 27.1% more than baselines). We then propose a defense algorithm called SockDef and show that it mitigates the impact of SockAttack (up to 69.2% with respect to F1-score).
Original language | English (US) |
---|---|
Pages (from-to) | 5253-5265 |
Number of pages | 13 |
Journal | IEEE Transactions on Computational Social Systems |
Volume | 11 |
Issue number | 4 |
DOIs | |
State | Published - 2024 |
Funding
This work was supported by ONR under Grant N00014-18-1-2670 and Grant N00014-20-1-2407.
Keywords
- Deep Learning
- Markov processes
- electronic commerce
- fraud
ASJC Scopus subject areas
- Modeling and Simulation
- Social Sciences (miscellaneous)
- Human-Computer Interaction