Zhuotao Lian, Weiyu Wang, Qingkui Zeng, Toru Nakanishi 0001, Teruaki Kitasuka, Chunhua Su. Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior. In Jiageng Chen, Debiao He, Wei Xie 0008, editors, Network and System Security - 19th International Conference, NSS 2025, Wuhan, China, December 5-7, 2025, Proceedings. Volume 16326 of Lecture Notes in Computer Science, pages 146-160, Springer, 2025. [doi]
Abstract is missing.