mlsanityData to 7 Oct 2026

Instructional Fingerprinting of Large Language Models

arXiv 2401.12255 ↗First posted 21 Jan 2024cs.CR cs.AI cs.CLcited by 64

Not on the map. Why?

Abstract (arXiv)

The exorbitant cost of training Large language models (LLMs) from scratch makes it essential to fingerprint the models to protect intellectual property via ownership authentication and to ensure downstream users and developers comply with their license terms (e.g. restricting commercial use). In this study, we present a pilot study on LLM fingerprinting as a form of very lightweight instruction tuning. Model publisher specifies a confidential private key and implants it as an instruction backdoor that causes the LLM to generate specific text when the key is present. Results on 11 popularly-used LLMs showed that this approach is lightweight and does not affect the normal behavior of the model. It also prevents publisher overclaim, maintains robustness against fingerprint guessing and parameter-efficient training, and supports multi-stage fingerprinting akin to MIT License. Code is available in https://cnut1648.github.io/Model-Fingerprint/.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 54 of its 78 references that are in the map. First posted on arXiv 21 Jan 2024.

Builds on

54 of 78 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2016Layer Normalizationcited by 5,579
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  7. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  8. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  9. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  10. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  11. 2020Extracting Training Data from Large Language Modelscited by 2,144
  12. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
38 more
  1. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  3. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  4. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  5. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  6. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  7. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  8. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 960
  9. 2018Neural Network Acceptability Judgmentscited by 952
  10. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  11. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  12. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  13. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 776
  14. 2023Large Language Modelscited by 774
  15. 2017Crowdsourcing Multiple Choice Science Questionscited by 742
  16. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 679
  17. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  18. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 478
  19. 2021MetaICL: Learning to Learn In Contextcited by 450
  20. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  21. 2018WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representationscited by 370
  22. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 318
  23. 2023Robust Distortion-free Watermarks for Language Modelscited by 279
  24. 2020Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learningcited by 216
  25. 2019A backdoor attack against LSTM-based text classification systemscited by 214
  26. 2018ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehensioncited by 198
  27. 2021Meta-learning via Language Model In-context Tuningcited by 163
  28. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 136
  29. 2019HEAD-QA: A Healthcare Dataset for Complex Reasoningcited by 100
  30. 2023LLM360: Towards Fully Transparent Open-Source LLMscited by 100
  31. 2021Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Modelscited by 96
  32. 2024Investigating Data Contamination for Pre-training Language Modelscited by 91
  33. 2023Protecting Language Generation Models via Invisible Watermarkingcited by 81
  34. 2021Protecting Intellectual Property of Language Generation APIs with Lexical Watermarkcited by 78
  35. 2022CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarkscited by 68
  36. 2023Watermarking Text Generated by Black-Box Language Modelscited by 68
  37. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermarkcited by 61
  38. 2022Watermarking Pre-trained Language Models with Backdooringcited by 44

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 29; 2026: 23.

64 papers.

Sort:

By area:

  1. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  2. 2024Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Techniquecited by 34
  3. 2024REEF: Representation Encoding Fingerprints for Large Language Modelscited by 34
  4. 2025We Should Chart an Atlas of All the World's Modelscited by 25
  5. 2024Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Mergingcited by 17
  6. 2025Auditing Black-Box LLM APIs with a Rank-Based Uniformity Testcited by 16
  7. 2024ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Modelscited by 15
  8. 2025Model Provenance Testing for Large Language Modelscited by 15
  9. 2024Mitigating Backdoor Threats to Large Language Models: Advancement and Challengescited by 14
  10. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 14
  11. 2025DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillationcited by 14
  12. 2025Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classificationcited by 13
38 more
  1. 2024The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resourcescited by 11
  2. 2025Scalable Fingerprinting of Large Language Modelscited by 11
  3. 2025Blackbox Model Provenance via Palimpsestic Membership Inferencecited by 11
  4. 2025Independence Tests for Language Modelscited by 10
  5. 2025SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained Fromcited by 9
  6. 2024SOS! Soft Prompt Attack Against Open-Source Large Language Modelscited by 7
  7. 2024Watermarking Language Models through Language Modelscited by 7
  8. 2025LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysiscited by 7
  9. 2025LLM Fingerprinting via Semantically Conditioned Watermarkscited by 7
  10. 2025CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Modelscited by 7
  11. 2025Riemannian-Geometric Fingerprints of Generative Modelscited by 7
  12. 2025Are Robust LLM Fingerprints Adversarially Robust?cited by 7
  13. 2025Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoptioncited by 7
  14. 2026On Protecting Agentic Systems' Intellectual Property via Watermarkingcited by 7
  15. 2024SVIP: Towards Verifiable Inference of Open-source Large Language Modelscited by 6
  16. 2025The Challenge of Identifying the Origin of Black-Box Large Language Modelscited by 5
  17. 2025ImF: Implicit Fingerprint for Large Language Modelscited by 5
  18. 2026Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspectivecited by 5
  19. 2025Invisible Traces: Using Hybrid Fingerprinting to identify underlying LLMs in GenAI Appscited by 4
  20. 2025Who Owns the Output? Bridging Law and Technology in LLMs Attributioncited by 4
  21. 2025Probing Neural Topology of Large Language Modelscited by 4
  22. 2025AWM: Accurate Weight-Matrix Fingerprint for Large Language Modelscited by 3
  23. 2026Sequential Behavioral Watermarking for LLM Agentscited by 3
  24. 2026KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditingcited by 3
  25. 2024Large Language Models as Carriers of Hidden Messagescited by 2
  26. 2024Watermarking Large Language Models and the Generated Content: Opportunities and Challengescited by 2
  27. 2025Towards the Resistance of Neural Network Watermarking to Fine-tuningcited by 2
  28. 2025FPEdit: Robust LLM Fingerprinting through Localized Parameter Editingcited by 2
  29. 2025SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprintingcited by 2
  30. 2026Invariant Features in Language Models: Geometric Characterization and Model Attributioncited by 2
  31. 2026Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thoughtcited by 2
  32. 2025Matrix-Driven Identification and Reconstruction of LLM Weight Homologycited by 1
  33. 2025Attacks and Defenses Against LLM Fingerprintingcited by 1
  34. 2025ActiveMark: on watermarking of visual foundation models via massive activationscited by 1
  35. 2025Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Modelscited by 1
  36. 2026ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Modelscited by 1
  37. 2026Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Softwarecited by 1
  38. 2026Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMscited by 1

50 most cited of 64 All 64 (JSON)