Year: 2026
Type: conference-paper
Abstract: The tremendous commercial potential of large language models (LLMs) has heightened concerns over their unauthorized use.To address this, we focus on the task of identifying the origin of black-box LLMs.We further propose PlugAE, an effective and efficient identification method that proactively leverages LLMspecific adversarial embeddings and allows users to customize copyright tokens on a targeted query set.Extensive experiments demonstrate that PlugAE outperforms both state-ofthe-art model watermarking and fingerprinting methods in accuracy and robustness.We further analyze its stealthiness and reliability from three complementary perspectives and conduct ablation studies under various configurations, confirming its practicality for real-world misuse detection.
Authors: Ziqing Yang, Yixin Wu, Yun Shen, Wei Dai, Michael Backes, Yang Zhang
Institution: Helmholtz Center for Information Security
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4416082603