Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm
Jiajie Su, Zihan Nan, Yunshan Ma +6
Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poiso…
cs.LG2024
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Xinting Liao, Weiming Liu, Pengyang Zhou +6
Federated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge. However, deploying FL models in real-world scenar…