SemanticShield uses a two-stage LLM detector that audits item descriptions in real-time. The paper was submitted in September 2025 and the code is on GitHub. https://getnews.me/semanticshield-llm-powered-audits-reveal-shilling-attacks-in-recommender-systems/ #semanticshield #recommendersystems

Kaihong Li, Huichi Zhou, Bin Ma, Fangjun Huang
SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
https://arxiv.org/abs/2509.24961

Kaihong Li, Huichi Zhou, Bin Ma, Fangjun Huang: SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems https://arxiv.org/abs/2509.24961 https://arxiv.org/pdf/2509.24961 https://arxiv.org/html/2509.24961