Language Model Fingerprinting

Follow this topic Ask about this topic

Language model fingerprinting studies how to identify a model, verify its ownership, or trace its lineage from evidence left by its behavior or structure. Black-box methods analyze responses to targeted prompts, token distributions, writing style, or agent actions, while white-box methods compare weights, activations, and attention patterns; watermarking deliberately embeds a detectable signal. These techniques support audits of API substitutions and model adaptations, attribution of generated text, and verification after fine-tuning, quantization, or distillation. A central challenge is making evidence reliable across deployment changes and adversarial imitation without confusing model identity with prompt, domain, or serving-system effects.

Latest papers

81 papers8 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
May 14, 2026William Lugoloobi, Samuelle Marro, Jabez Magomere +2Language Model Fingerprinting LLM Agent Security
Oxford Internet Institute, University of Oxford · Department of Engineering Science, University of Oxford
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
May 12, 2026Tom Sander, Hongyan Chang, Tomáš Souček +10Language Model Fingerprinting LLM Watermarking
FAIR, Meta Superintelligence Labs
Visual Fingerprints for LLM Generation Comparison
May 7, 2026Amal Alnouri, Andreas Hinterreiter, Christina Humer +2LLM Evaluation Language Model Fingerprinting
Johannes Kepler University Linz · ETH Zürich · Independent Researcher
The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive
Apr 28, 2026Alex Bogdan, Adrian de Valois-FranklinLLM Evaluation Language Model Generation Evaluation
Evolutionairy AI Toronto, Canada
Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
Apr 20, 2026Sinan G. Aksoy, Alexandra A. Sabrio, Erik VonKaenel +1Semantic Textual Similarity LLM-as-a-Judge
Pacific Northwest National Laboratory · Washington University in St. Louis · Humana Inc.
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
Apr 20, 2026Zirui Wang, Yusen Hou, Shaofeng Liang +4LLM Auditing Language Model Fingerprinting
The Hong Kong University of Science and Technology (Guangzhou) · Deep Interdisciplinary Intelligence Lab (DI2Lab)
SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
Apr 18, 2026Yifei Zhao, Qian Lou, Mengxin ZhengVLM Robustness Language Model Fingerprinting
University of Central Florida
AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
Apr 7, 2026Haobo Zhang, Zhenhua Xu, Junxian Li +3Language Model Fingerprinting Data Provenance in Language Models
Zhejiang University of Technology · Binjiang Institute of Zhejiang University · Zhejiang University +2
StoryScope: Investigating idiosyncrasies in AI fiction
Apr 3, 2026Jenna Russell, Rishanth Rajendhran, Chau Minh Pham +2AI-Generated Text Detection Authorship Attribution
University of Maryland, College Park · Google DeepMind
Who Wrote the Book? Detecting and Attributing LLM Ghostwriters
Mar 30, 2026Anudeex Shetty, Qiongkai Xu, Olga Ohrimenko +1OOD Generalization Language Model Fingerprinting
School of Computing and Information Systems, The University of Melbourne, Australia · School of Computing, FSE, Macquarie University, Australia
The Last Fingerprint: How Markdown Training Shapes LLM Prose
Mar 27, 2026E. M. FreeburgLLM Training Language Model Fingerprinting
Independent Researcher
GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution
Mar 24, 2026Nitin Choudhury, Bikrant Bikram Pratap Maurya, Bhavinkumar Vinodbhai Kuwar +1Authorship Attribution Language Model Fingerprinting
Behavioral Fingerprints for LLM Endpoint Stability and Identity
Mar 19, 2026Jonah Leshin, Manish Shah, Ian Timmis +1LLM Reliability Language Model Fingerprinting
Project VAIL, San Francisco, USA · University of Illinois Urbana-Champaign, Department of Computer Science, Urbana, Illinois, USA
InterPol: De-anonymizing LM Arena via Interpolated Preference Learning
Mar 16, 2026Minsung Cho, Jaehyung KimLanguage Model Fingerprinting Privacy Leakage in Language Models
Yonsei University
Interpretable Predictability-Based AI Text Detection: A Replication Study
Mar 16, 2026Adam Skurla, Dominik Macko, Jakub SimkoAI-Generated Text Detection Language Model Fingerprinting
Faculty of Information Technology, Brno University of Technology, Brno, Czechia · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia
Code Fingerprints: Disentangled Attribution of LLM-Generated Code
Mar 4, 2026Jiaxun Guo, Ziyuan Yang, Mengyu Sun +3Language Model Fingerprinting Code Language Models
School of Cyber Science and Engineering, Sichuan University, Chengdu, China
SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting
Dec 3, 2025Hanxiu Zhang, Qiang Xu, Yue ZhengLanguage Model Fingerprinting LLM Security
The Chinese University of Hong Kong, Shenzhen
From Construction to Injection: Edit-Based Fingerprints for Large Language Models
Sep 3, 2025Yue Li, Xin Yi, Dongsheng Shi +3Language Model Fingerprinting LLM Security
East China Normal University · Hasso Plattner Institute/University of Potsdam
RAFP: Identifying LLM Lineages via Rare-Region Fingerprints
May 19, 2025Yun-Yun Tsai, Jia Hao Liang, Chuan Guo +2Language Model Fingerprinting Language Model Robustness
Columbia University / Meta · New York / Menlo Park, USA · MIT +5
The Challenge of Identifying the Origin of Black-Box Large Language Models
Mar 6, 2025Ziqing Yang, Yixin Wu, Yun Shen +3Language Model Fingerprinting LLM Security
CISPA Helmholtz Center for Information Security · NetApp · TikTok Inc.
Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
Jul 15, 2024Mark Russinovich, Yanan Cai, Ahmed SalemLanguage Model Fingerprinting
Microsoft

May 14, 2026J/K move · Enter open · S save

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

William Lugoloobi, Samuelle Marro, Jabez Magomere, Joss Wright+1

Oxford Internet Institute, University of Oxford · Department of Engineering Science, University of Oxford

Language Model Fingerprinting LLM Agent Security

Open paper AskPDF arXiv

As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerabilities. Across 14 frontier LLMs and four web environments spanning information retrieval and shopping tasks, we show that an agent's actions and interaction timings, captured via a passive JavaScript tracker, are sufficient to identify the underlying model with up to 96% F1. We formalise this attack surface by demonstrating that classifiers trained on agent actions generalise across model sizes and families. We further show that strong classifiers can be trained from few interaction traces and that agent identity can be inferred early within an episode. Injecting randomised timing delays between actions substantially degrades classifier performance, but does not provide robust protection: a classifier retrained on delayed traces largely recovers performance. We release our harness and a labelled corpus of agent traces here.