GREW uses a secret-key-driven green-red item partition and three ranking-integrated modules to embed verifiable watermarks in recommender systems that resist extraction attacks without data injection.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SharpAP enhances transferability of injective poisoning attacks on recommender systems by formulating them as a tri-level optimization that seeks and attacks an approximately worst-case victim model using sharpness-aware minimization.
citing papers explorer
-
Green-Red Watermarking for Recommender Systems
GREW uses a secret-key-driven green-red item partition and three ranking-integrated modules to embed verifiable watermarks in recommender systems that resist extraction attacks without data injection.
-
Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systems
SharpAP enhances transferability of injective poisoning attacks on recommender systems by formulating them as a tri-level optimization that seeks and attacks an approximately worst-case victim model using sharpness-aware minimization.