mlsanityData to 14 Oct 2026

REEF: Representation Encoding Fingerprints for Large Language Models

arXiv 2410.14273 ↗First posted 18 Oct 2024cs.CL cs.AI cs.CRcited by 36

Not on the map. Why?

Abstract (arXiv)

Protecting the intellectual property of open-source Large Language Models (LLMs) is very important, because training LLMs costs extensive computational resources and data. Therefore, model owners and third parties need to identify whether a suspect model is a subsequent development of the victim model. To this end, we propose a training-free REEF to identify the relationship between the suspect and victim models from the perspective of LLMs' feature representations. Specifically, REEF computes and compares the centered kernel alignment similarity between the representations of a suspect model and a victim model on the same samples. This training-free REEF does not impair the model's general capabilities and is robust to sequential fine-tuning, pruning, model merging, and permutations. In this way, REEF provides a simple and effective way for third parties and models' owners to protect LLMs' intellectual property together. The code is available at https://github.com/tmylla/REEF.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 46 of its 62 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

46 of 62 references.

References · 46

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  5. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  6. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  9. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
  10. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  11. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 800
  12. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
34 more
  1. 2023A Watermark for Large Language Modelscited by 725
  2. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
  3. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 625
  4. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 422
  5. 2023Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningcited by 415
  6. 2023Llemma: An Open Language Model For Mathematicscited by 388
  7. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  8. 2023Efficient and Effective Text Encoding for Chinese LLaMA and Alpacacited by 305
  9. 2023A Survey on Model Compression for Large Language Modelscited by 269
  10. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 253
  11. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 230
  12. 2024Evolutionary Optimization of Model Merging Recipescited by 208
  13. 2024Knowledge Fusion of Large Language Modelscited by 115
  14. 2023LLM360: Towards Fully Transparent Open-Source LLMscited by 104
  15. 2023Protecting Language Generation Models via Invisible Watermarkingcited by 90
  16. 2024Instructional Fingerprinting of Large Language Modelscited by 68
  17. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermarkcited by 67
  18. 2019How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNNcited by 66
  19. 2024Model Compression and Efficient Inference for Large Language Models: A Surveycited by 64
  20. 2024LLMmap: Fingerprinting For Large Language Modelscited by 58
  21. 2023The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Modelscited by 55
  22. 2024FuseChat: Knowledge Fusion of Chat Modelscited by 55
  23. 2020Methods for Pruning Deep Neural Networkscited by 49
  24. 2024Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Techniquecited by 37
  25. 2023HuRef: HUman-REadable Fingerprint for Large Language Modelscited by 34
  26. 2024Your Large Language Models Are Leaving Fingerprintscited by 33
  27. 2023Beyond Surface Statistics: Scene Representations in a Latent Diffusion Modelcited by 30
  28. 2023Beyond Size: How Gradients Shape Pruning Decisions in Large Language Modelscited by 30
  29. 2024A Fingerprint for Large Language Modelscited by 28
  30. 2024Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learningcited by 18
  31. 2024MLP Can Be A Good Transformer Learnercited by 17
  32. 2023Functional Invariants to Watermark Large Transformerscited by 15
  33. 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 14
  34. 2023High-frequency Matters: An Overwriting Attack and defense for Image-processing Neural Network Watermarkingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 21; 2026: 14.

36 papers.

Sort:

By area:

  1. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  2. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  3. 2025Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trendscited by 20
  4. 2025Model Provenance Testing for Large Language Modelscited by 15
  5. 2025SoK: Large Language Model Copyright Auditing via Fingerprintingcited by 15
  6. 2025Scalable Fingerprinting of Large Language Modelscited by 14
  7. 2025Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classificationcited by 14
  8. 2025Blackbox Model Provenance via Palimpsestic Membership Inferencecited by 11
  9. 2025FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprintcited by 10
  10. 2025Independence Tests for Language Modelscited by 10
  11. 2025SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained Fromcited by 10
  12. 2025LLM Fingerprinting via Semantically Conditioned Watermarkscited by 9
24 more
  1. 2025Are Robust LLM Fingerprints Adversarially Robust?cited by 8
  2. 2025PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attentioncited by 4
  3. 2025FPEdit: Robust LLM Fingerprinting through Localized Parameter Editingcited by 3
  4. 2025Understanding Post-Training Structural Changes in Large Language Modelscited by 3
  5. 2025AWM: Accurate Weight-Matrix Fingerprint for Large Language Modelscited by 3
  6. 2025Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoringcited by 2
  7. 2025Towards the Resistance of Neural Network Watermarking to Fine-tuningcited by 2
  8. 2025Model Correlation Detection via Random Selection Probingcited by 2
  9. 2025SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprintingcited by 2
  10. 2026SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Modelscited by 2
  11. 2026ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Modelscited by 1
  12. 2026Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMscited by 1
  13. 2026Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Contentcited by 1
  14. 2026Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verificationcited by 1
  15. 2025Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distributioncited by 0
  16. 2026DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protectioncited by 0
  17. 2026Symmetric Divergence and Normalized Similarity: A Unified Topological Framework for Representation Analysiscited by 0
  18. 2026The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoderscited by 0
  19. 2026Black-Box Inference of LLM Architectural Properties with Restrictive API Accesscited by 0
  20. 2026Spectral Signatures of Large Language Modelscited by 0
  21. 2026Stemma: Induced Decision Regions Reveal LLM Provenancecited by 0
  22. 2026Witness Overlap: Directional Provenance Inside Open-Weight Model Familiescited by 0
  23. 2026Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Modelscited by 0
  24. 2026Language Model Fingerprinting Requires Rethinking Watermark Teacherscited by 0