aiqbench analysis
This research introduces PlugAE, a novel method for identifying the origin of black-box large language models using adversarial embeddings and customizable copyright tokens. The study demonstrates that this approach surpasses existing watermarking and fingerprinting techniques in both accuracy and robustness while maintaining stealthiness against detection attempts. These findings are critical for addressing unauthorized model usage and enhancing security protocols within the AI ecosystem.
The Challenge of Identifying the Origin of Black-Box Large Language Models
arXiv:2503.04332v2 Announce Type: replace-cross 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 LLM-specific adversarial embeddings and allows users to customize copyright tokens on a targeted query set. Extensive experiments demonstrate that PlugAE outperforms both state-of-the-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.
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 LLM-specific adversarial embeddings and allows users to customize copyright tokens on a targeted query set. Extensive experiments demonstrate that PlugAE outperforms both state-of-the-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.
Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2503.04332 [cs.CR]
(or arXiv:2503.04332v2 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2503.04332 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 197 words
Related coverage
[AINews] not much happened today
Latent Space · Sep 18, 2026
MedPAIR: Measuring Whether Physicians and AI Agree on What Matters in Medical QA
Snorkel AI Blog · Oct 2, 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026
Why I Left Google DeepMind
LessWrong · Jul 15, 2026