Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought

arXiv:2405.07018v1 Announce Type: new
Abstract: Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users' membership privacy. However, existing MIAs relying on shadow training suffer a large performance drop when the attacker lacks knowledge of the training data distribution and the model architecture of the target recommender system. To better understand the privacy risks of recommender systems, we propose shadow-free MIAs …

applications arxiv attacks cs.cr free large performance privacy recommender systems shadow studies systems thought training vulnerable