Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systems

ArXi:2604.22170v1 Announce Type: new Recommender Systems~(RS) have been shown to be vulnerable to injective attacks, where attackers inject limited fake user profiles to promote the exposure of target items to real users for unethical gains (e.g., economic or political advantages). Since attackers typically lack knowledge of the victim model deployed in the target RS, existing methods resort to using a fixed surrogate model to mimic the potential victim model.