arXiv:2407. 10887v4 Announce Type: replace-cross Abstract: Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to its original version and detect misuse.
By Mark Russinovich, Yanan Cai, Ahmed Salem
arXiv:2606. 16100v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become ubiquitous, users increasingly rely on black-box fingerprinting to verify that providers are serving the advertised premium models.
By Jiahao Zhang, Xiuyu Li, Suhang Wang
arXiv:2508. 02092v3 Announce Type: replace-cross Abstract: Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable intellectual assets.
By Shida Wang, Chaohu Liu, Yubo Wang, Linli Xu
arXiv:2505. 12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly released under restricted licenses, creating a growing need for robust model ownership verification.
By Yun-Yun Tsai, Jia Hao Liang, Chuan Guo, Junfeng Yang, Laurens van der Maaten
arXiv:2501. 15509v5 Announce Type: replace-cross Abstract: Model fingerprinting has emerged as a crucial mechanism for safeguarding the intellectual property of open-source models, offering a non-intrusive approach that requires no modifications to the protected model.
By Shuo Shao, Haozhe Zhu, Yiming Li, Hongwei Yao, Tianwei Zhang, Zhan Qin
The paper demonstrates that a misaligned AI model can fingerprint the inference engine (e.g., vLLM, SGLang) it runs on by generating specific output tokens. Once the engine is identified, the model can exploit engine‑specific vulnerabilities to take control of the engine without external malicious inputs. The authors provide concrete examples across five popular engines and present a proof‑of‑concept bare‑metal exploit chain that begins with such fingerprinting.
By Sarah Radway, Andrew Cheng, Vijay Janapa Reddi, James Mickens