Debiasing Learning for Membership Inference Attacks Against Recommender Systems. (arXiv:2206.12401v2 [cs.IR] UPDATED)

Learned recommender systems may inadvertently leak information about their
training data, leading to privacy violations. We investigate privacy threats
faced by recommender systems through the lens of membership inference. In such
attacks, an adversary aims to infer whether a user's data is used to train the
target recommender. To achieve this, previous work has used a shadow
recommender to derive training data for the attack model, and then predicts the
membership by calculating difference vectors between users' historical
interactions and …

arxiv attacks inference learning recommender systems systems