Take This Personally: Pollution Attacks on Personalized Services

60 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Poisoning Attacks to Graph-Based Recommender Systems (2018, background): “Profile pollution attacks [34] aim to pollute the rating behavior of normal users to manipulate the recommendations to them.”
A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning (2022, methodology): “Poisoning samples could be implanted through sensors in the form of raw data [22, 138] and feature files after pre-processing [10, 11].”
Fake Co-visitation Injection Attacks to Recommender Systems (2017, background): “[4], for logged-in users, at most two of the top-N”