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.

AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
Oct 23, 2026Gejian Zhao, Hanzhou Wu, Xinpeng ZhangLanguage Model Fingerprinting AI Agent Security
Shanghai University
Every Model Leaves a Trace: Multi-Resolution LLM Fingerprinting
Oct 20, 2026Mohammad Reza Modarres, Armin Tourajmehr, Artin Tavasoli +2Language Model Fingerprinting Language Model Robustness
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · Tehran Institute for Advanced Studies, Khatam University, Iran · Cardiff University, United Kingdom
Forty Questions: Identifying a Language Model from One-Word Answers
Oct 20, 2026Tapan ParikhLanguage Model Fingerprinting LLM Auditing
Cornell Tech
Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution
Oct 19, 2026Ziyi Zhang, Ziyao Wang, Guoheng Sun +2LLM Auditing LLM Watermarking
Stony Brook University · University of Maryland, College Park
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
Oct 8, 2026Teruki Sano, Minoru Kuribayashi, Masao Sakai +4Language Model Fingerprinting
Graduate School of Information Sciences, Tohoku University, Japan · Center for Data-driven Science and Artificial Intelligence, Tohoku University, Japan
Language Model Fingerprinting Requires Rethinking Watermark Teachers
Oct 3, 2026Jeongyeon Hwang, Anshul Nasery, Sewoong Oh +1Language Model Fingerprinting Fingerprint Identification
Pohang University of Science and Technology · University of Washington
Emergent Structure in the Marginal Attention Space of Language Models
Oct 2, 2026Valentino Maiorca, Walter Nelson, Francesco LocatelloAttention Mechanisms Attention Head Analysis
Institute of Science and Technology Austria (ISTA)
Forging LLM Authorship Fingerprints with Targeted Rewriting
Sep 30, 2026Haohan Yuan, Simin Chen, Xi Niu +3Language Model Fingerprinting Adversarial Text Attacks
University of North Carolina at Charlotte · George Mason University · Indiana University
A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
Sep 25, 2026Shahrooz Pouryousef, Jesus Lopez, Saeefa Rubaiyat Nowmi +4LLM Security Privacy Leakage in Language Models
Chalmers University of Technology, Sweden · University of Texas at El Paso, USA · Old Dominion University, USA +1
Where a Model Sends Its Own Repeated Token
Sep 25, 2026Nicolás Vera ZúñigaLanguage Model Fingerprinting Language Model Probing
Independent Researcher, Chile
Witness Overlap: Directional Provenance Inside Open-Weight Model Families
Sep 24, 2026Siyuan Li, Haoxuan Zeng, Xin Luo +6LLM Auditing Open-Weight Language Models
ModelOS · University of Michigan · Carnegie Mellon University
Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models
Sep 24, 2026Ehsan Barkhordar, Surendrabikram ThapaLanguage Model Fingerprinting Code Language Models
Koç University · Virginia Tech
System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer
Sep 23, 2026Dmitrij ŻatuchinLLM Auditing Language Model Fingerprinting
Department of Information Technologies, Estonian Entrepreneurship University of Applied Sciences (EUAS), Tallinn, Estonia.
Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
Sep 23, 2026Chuyi Wang, Xiaohui Xie, Tongze Wang +2Coding Agents Language Model Fingerprinting
Department of Computer Science and Technology, Tsinghua University
From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models
Sep 21, 2026Jiaxin Hong, Yuxin Peng, Hongyao Yu +3Language Model Fingerprinting LLM Security
Harbin Institute of Technology, Shenzhen · South China University of Technology · Tsinghua Shenzhen International Graduate School, Tsinghua University
Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling
Sep 19, 2026Yu Sha, Junqi Tao, Dixin Zhou +10Personality Modeling in Language Models Multilingual Language Model Evaluation
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, China. · Key Laboratory of Quark & Lepton Physics and Institute of Particle Physics, Central China Normal University, Wuhan, 430079, China. · Shandong Science and Technology Press, Shandong Publishing Group, Jinan, 250003, China. +6
Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
Sep 17, 2026Sarah Radway, Andrew Cheng, Vijay Janapa Reddi +1Language Model Fingerprinting Software Security
Harvard University
Fingerprinting Multimodal Large Language Models
Sep 17, 2026Chao Huang, Meng Tong, Kejiang ChenLLM Auditing Language Model Fingerprinting
University of Science and Technology of China Anhui Province Key Laboratory of Digital Security Hefei, Anhui, China
SlopShape: Identifying AI-Generated Commercial Web Content
Sep 14, 2026Jochen MadlerAI-Generated Text Detection Language Model Fingerprinting
Sitefire
Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
Aug 31, 2026Yisen XiLanguage Model Fingerprinting Black-Box Model Auditing
Independent Researcher, Beijing, China
Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting
Aug 30, 2026Bo ChenLLM Evaluation Language Model Fingerprinting
Institute of Computing Technology, Chinese Academy of Sciences
AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes
Aug 30, 2026Xun Wang, Bihe Zhao, Michael Backes +2LLM Auditing Language Model Fingerprinting
CISPA Helmholtz Center for Information Security
AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not
Aug 28, 2026Zhengyang Shan, Yukyung Lee, Sophie HaoAI-Generated Text Detection Language Model Fingerprinting
Boston University
Diff Mining: Logit Differences Reveal Finetuning Objectives
Aug 26, 2026Greg Kocher, Robert West, Clément Dumas +1LLM Fine-Tuning Language Model Auditing
Independent · EPFL · ENS Paris-Saclay, Université Paris-Saclay +1
Beyond Capability Benchmarks: Learning Operational Fingerprints of LLM Cloud Services from Production Incident Metadata
Aug 26, 2026Meiwei Zhang, Eduardo Miranda, Bruce Baynes +4LLM Serving Language Model Fingerprinting
Google Cloud Platform, Google LLC
Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification
Aug 14, 2026Aman Singh Thakur, Rayan KhouryLanguage Model Fingerprinting Open-Weight Language Models
Massachusetts Institute of Technology, USA
Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models
Aug 12, 2026Junpeng Wang, Yuzhong Chen, Menghai Pan +2Code Language Models LLM Evaluation
Visa Research
Identifying Intelligent Processes via Online Sequential Testing
Aug 10, 2026Aritra Das, Debayan GuptaLanguage Model Fingerprinting Sequential Hypothesis Testing
Truth Audit Labs
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification
Aug 8, 2026Yutong Wu, Xiaofan Bai, Shixin Li +10Language Model Fingerprinting
Huazhong University of Science and Technology · Alibaba Group · Microsoft Corporation
TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance
Aug 8, 2026Yuqi Wu, Shengming Zhao, Jie ChenLLM Auditing Language Model Fingerprinting
College of Biomedical Engineering, Fudan University

Oct 23, 2026J/K move · Enter open · S save

AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents

Gejian Zhao, Hanzhou Wu, Xinpeng Zhang

Shanghai University

Language Model Fingerprinting AI Agent Security Data Provenance in Language Models

Open paper AskPDF arXiv

Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active watermarking conflicts with schema-constrained tool generation. We propose AgentTrace, an active framework that identifies the foundation model behind a black-box agent via observable execution traces. AgentTrace injects structurally ambiguous probes to trigger tokenization-sensitive serialization failures at rigid tool interfaces. While these initial failures provide coarse-grained separation across model families, the temporal sequence of subsequent repair operations reveals fine-grained, model-specific recovery behaviors. By modeling these multi-step trajectories with lightweight Markov chains, AgentTrace achieves 96.0% attribution accuracy under adversarial identity spoofing. Crucially, sequential repair modeling successfully distinguishes the evaluated intra-family variants sharing identical tokenizers (e.g., Llama-3 8B/70B), substantially outperforming unordered behavioral statistics while remaining robust against prompt obfuscation and temperature scaling.