arXiv Machine Learning July 14, 2026 By Tomas Bruckner

One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions

Read the original on arXiv Machine Learning →

arXiv:2607. 10252v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Aug 11

Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification

arXiv:2608. 08195v1 Announce Type: cross Abstract: Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment.

By Yutong Wu, Xiaofan Bai, Shixin Li, Pingyi Hu, Ziqi Zhou, Zilong Wang, Xiaojing Ma, Songfeng Lu, Yuhong Li, Jin Xuan, Yi Wang, Dongmei Zhang, Bin Benjamin Zhu

llms fine-tuning efficiency safety

arXiv Machine Learning

Jul 1

Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?

arXiv:2606. 32008v1 Announce Type: new Abstract: Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens.

By Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo, Chia-Tse Shao, Yingxiao Ye, Aobo Yang, Vivek Miglani, Nehal Bandi

llms safety

arXiv AI

Jul 2

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

arXiv:2607. 01208v1 Announce Type: cross Abstract: Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale.

By Shayan Talaei, Abhinav Chinta, Devvrit Khatri, Amin Karbasi, Azalia Mirhoseini, Amin Saberi

llms efficiency safety

arXiv Machine Learning

Jul 15

RAFP: Identifying LLM Lineages via Rare-Region Fingerprints

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

llms fine-tuning efficiency safety

arXiv Machine Learning

Jun 16

Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services

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

llms fine-tuning efficiency safety

arXiv AI

Aug 11

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance

arXiv:2608. 08139v1 Announce Type: new Abstract: Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challenge that metadata alone cannot resolve.

By Yuqi Wu, Shengming Zhao, Jie Chen

llms nlp efficiency benchmarks

Related stories

Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification

Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

RAFP: Identifying LLM Lineages via Rare-Region Fingerprints

Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services

TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance