@inproceedings{zhang-etal-2026-copyright,
    title = "Copyright Detective: A Forensic System to Evidence {LLM}s Flickering Copyright Leakage Risks",
    author = "Zhang, Guangwei  and
      Zhu, Jianing  and
      Qian, Cheng  and
      Gong, Neil Zhenqiang  and
      Mihalcea, Rada  and
      Xu, Zhaozhuo  and
      He, Jingrui  and
      Ma, Jiaqi W.  and
      Xiao, Chaowei  and
      Li, Bo  and
      Abbasi, Ahmed  and
      Lee, Dongwon  and
      Ji, Heng  and
      Zhang, Denghui",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.2/",
    pages = "14--26",
    ISBN = "979-8-89176-392-0",
    abstract = "We present **Copyright Detective**, the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs. The system treats copyright infringement versus compliance as an **evidence discovery** process rather than a static classification task due to the complex nature of copyright law. It integrates multiple detection paradigms, including content recall testing, paraphrase-level similarity analysis, persuasive jailbreak probing, and unlearning verification, within a unified and extensible framework. Through interactive prompting, response collection, and iterative workflows, our system enables systematic auditing of verbatim memorization and paraphrase-level leakage, supporting responsible deployment and transparent evaluation of LLM copyright risks even with black-box access. In our experiments with GPT-4o-mini, we demonstrate that the specific persuasive strategy ``Pathos'' shifts the leakage distribution from about 0.1 (ROUGE-L) to 0.7. Our live system is hosted on [Streamlit server](https://copyright-detective.streamlit.app), with a [demonstration video](https://youtu.be/z9Lh4kNDHiM) included as supplementary material."
}