mlsanityData to 14 Oct 2026

The Challenge of Identifying the Origin of Black-Box Large Language Models

arXiv 2503.04332 ↗First posted 6 Mar 2025cs.CR cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

The tremendous commercial potential of large language models (LLMs) has heightened concerns over their unauthorized use. To address this, we focus on the task of identifying the origin of black-box LLMs. We further propose PlugAE, an effective and efficient identification method that proactively leverages LLM-specific adversarial embeddings and allows users to customize copyright tokens on a targeted query set. Extensive experiments demonstrate that PlugAE outperforms both state-of-the-art model watermarking and fingerprinting methods in accuracy and robustness. We further analyze its stealthiness and reliability from three complementary perspectives and conduct ablation studies under various configurations, confirming its practicality for real-world misuse detection.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 63 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

35 of 63 references.

References · 35

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  7. 2023Visual Instruction Tuningcited by 7,869
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  10. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  11. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  12. 2023Code Llama: Open Foundation Models for Codecited by 2,139
23 more
  1. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  2. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  3. 2023A Watermark for Large Language Modelscited by 725
  4. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  5. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 654
  6. 2024OLMo: Accelerating the Science of Language Modelscited by 613
  7. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  8. 2023Provable Robust Watermarking for AI-Generated Textcited by 299
  9. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
  10. 2023Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2cited by 229
  11. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 191
  12. 2023Orca 2: Teaching Small Language Models How to Reasoncited by 159
  13. 2023A Semantic Invariant Robust Watermark for Large Language Modelscited by 112
  14. 2023Robust Multi-bit Natural Language Watermarking through Invariant Featurescited by 82
  15. 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 70
  16. 2024Instructional Fingerprinting of Large Language Modelscited by 68
  17. 2022Watermarking Pre-trained Language Models with Backdooringcited by 50
  18. 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identificationcited by 36
  19. 2023HuRef: HUman-REadable Fingerprint for Large Language Modelscited by 34
  20. 2024Your Large Language Models Are Leaving Fingerprintscited by 33
  21. 2024Provably Robust Watermarks for Open-Source Language Modelscited by 13
  22. 2021Fingerprinting Fine-tuned Language Models in the Wildcited by 10
  23. 2024SOS! Soft Prompt Attack Against Open-Source Large Language Modelscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Servicescited by 3
  2. 2026Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generationcited by 2
  3. 2026Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMscited by 1
  4. 2025Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMscited by 0
  5. 2026Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprintingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
  2. 2025Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
  3. 2025SoK: Large Language Model Copyright Auditing via Fingerprinting
  4. 2023Baselines for Identifying Watermarked Large Language Models
  5. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
  6. 2025Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
  7. 2024A Watermark for Black-Box Language Models
  8. 2024Watermarking Large Language Models and the Generated Content: Opportunities and Challenges