作者位次 #3/6SIGIR 2026Oral· Information Retrieval (Full)
Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems
Yuchuan Zhao · Tong Chen · Junliang Yu · Zongwei Wang · Lizhen Cui · Hongzhi Yin
摘要
Large language model-powered sequential recommender systems (LLM-SRSs) have recently demonstrated remarkable performance, enabling recommendations through prompt-driven inference over user interaction sequences. However, this paradigm also introduces new security vulnerabilities, particularly tex...