mlsanityData to 7 Oct 2026

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models

arXiv 2405.02466 ↗First posted 3 May 2024cs.CR cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence (AI) field have open-sourced their original LLMs, an increasing number of individuals and smaller companies are able to build derivative LLMs based on these open-sourced models at much lower costs. However, this practice opens up possibilities for unauthorized use or reproduction that may not comply with licensing agreements, and fine-tuning can change the model's behavior, thus complicating the determination of model ownership. Current intellectual property (IP) protection schemes for LLMs are either designed for white-box settings or require additional modifications to the original model, which restricts their use in real-world settings. In this paper, we propose ProFLingo, a black-box fingerprinting-based IP protection scheme for LLMs. ProFLingo generates queries that elicit specific responses from an original model, thereby establishing unique fingerprints. Our scheme assesses the effectiveness of these queries on a suspect model to determine whether it has been derived from the original model. ProFLingo offers a non-invasive approach, which neither requires knowledge of the suspect model nor modifications to the base model or its training process. To the best of our knowledge, our method represents the first black-box fingerprinting technique for IP protection for LLMs. Our source code and generated queries are available at: https://github.com/hengvt/ProFLingo.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

23 of 35 references.

References · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2023Mistral 7Bcited by 3,065
  7. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  8. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  9. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  10. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  11. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  12. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 187
11 more
  1. 2023A Survey of Large Language Models in Medicine: Progress, Application, and Challengecited by 123
  2. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
  3. 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 90
  4. 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 68
  5. 2023A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trendscited by 66
  6. 2024Instructional Fingerprinting of Large Language Modelscited by 64
  7. 2021Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Modelscited by 44
  8. 2022Watermarking Pre-trained Language Models with Backdooringcited by 44
  9. 2024Large Language Models in Cybersecurity: State-of-the-Artcited by 34
  10. 2023HuRef: HUman-REadable Fingerprint for Large Language Modelscited by 32
  11. 2024Double-I Watermark: Protecting Model Copyright for LLM Fine-tuningcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 14
  2. 2025SoK: Large Language Model Copyright Auditing via Fingerprintingcited by 14
  3. 2025Blackbox Model Provenance via Palimpsestic Membership Inferencecited by 11
  4. 2025Independence Tests for Language Modelscited by 10
  5. 2025Are Robust LLM Fingerprints Adversarially Robust?cited by 7
  6. 2025AWM: Accurate Weight-Matrix Fingerprint for Large Language Modelscited by 3
  7. 2026FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequencescited by 3
  8. 2025FPEdit: Robust LLM Fingerprinting through Localized Parameter Editingcited by 2
  9. 2026SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Modelscited by 2
  10. 2025Towards Provable (In)Secure Model Weight Release Schemescited by 1
  11. 2026Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Contentcited by 1
  12. 2026Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verificationcited by 1
3 more
  1. 2026Stemma: Induced Decision Regions Reveal LLM Provenancecited by 0
  2. 2026Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Spacecited by 0
  3. 2026Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprintingcited by 0