mlsanityData to 14 Oct 2026

Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services

arXiv 2606.16100 ↗First posted 15 Jun 2026cs.CR cs.CL cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

As Large Language Model (LLM) APIs become ubiquitous, users increasingly rely on black-box fingerprinting to verify that providers are serving the advertised premium models. However, these methods may overlook adversarial providers who manipulate model weights to cheat the fingerprint process. We introduce a novel threat termed fingerprint spoofing, where a malicious provider stealthily serves a weaker model that has been parameter-efficiently fine-tuned to mimic a stronger model, thereby evading user-side fingerprinting. We first formally prove that user-side resource constraints (i.e., finite query budgets and weak fingerprinting classifiers) make current fingerprinting vulnerable to fingerprint spoofing. Guided by this theoretical analysis, we propose GhostPrint, a cost-effective attack framework leveraging surrogate modeling, reward-ranked fine-tuning, and knowledge distillation. Extensive evaluations in both static and continual fingerprinting settings demonstrate that GhostPrint allows weak models to consistently bypass representative fingerprint methods while maintaining utility at a low fine-tuning cost, exposing a critical vulnerability in current LLM fingerprinting pipelines.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 49 of its 77 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

49 of 77 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  8. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  9. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  10. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 839
  11. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 686
  12. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
37 more
  1. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
  2. 2023Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Lawscited by 159
  3. 2024Revisiting Catastrophic Forgetting in Large Language Model Tuningcited by 99
  4. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 88
  5. 2022Watermarking Pre-trained Language Models with Backdooringcited by 50
  6. 2024Model Equality Testing: Which Model Is This API Serving?cited by 47
  7. 2025Are You Getting What You Pay For? Auditing Model Substitution in LLM APIscited by 38
  8. 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identificationcited by 36
  9. 2024Your Large Language Models Are Leaving Fingerprintscited by 33
  10. 2025Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMscited by 21
  11. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarkingcited by 19
  12. 2026Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuningcited by 17
  13. 2025SoK: Large Language Model Copyright Auditing via Fingerprintingcited by 15
  14. 2025LLM DNA: Tracing Model Evolution via Functional Representationscited by 15
  15. 2025CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIscited by 14
  16. 2025Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classificationcited by 14
  17. 2025Is Your LLM Overcharging You? Tokenization, Transparency, and Incentivescited by 13
  18. 2025CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoorcited by 12
  19. 2025Blackbox Model Provenance via Palimpsestic Membership Inferencecited by 11
  20. 2025Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Servicescited by 10
  21. 2025SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained Fromcited by 10
  22. 2025LLM Fingerprinting via Semantically Conditioned Watermarkscited by 9
  23. 2026Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rolloutscited by 9
  24. 2025DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protectioncited by 8
  25. 2025Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Modelscited by 8
  26. 2025Are Robust LLM Fingerprints Adversarially Robust?cited by 8
  27. 2026Real Money, Fake Models: Deceptive Model Claims in Shadow APIscited by 8
  28. 2025Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimationcited by 7
  29. 2025Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providerscited by 6
  30. 2025The Challenge of Identifying the Origin of Black-Box Large Language Modelscited by 5
  31. 2025Speculating LLMs' Chinese Training Data Pollution from Their Tokenscited by 5
  32. 2026ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignmentcited by 5
  33. 2025SUA: Stealthy Multimodal Large Language Model Unlearning Attackcited by 4
  34. 2025RouteMark: A Fingerprint for Intellectual Property Attribution in Routing-based Model Mergingcited by 4
  35. 2025iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verificationcited by 4
  36. 2026URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Modelscited by 3
  37. 2026Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIscited by 0
  2. 2026AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probescited by 0
  3. 2026Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behaviorcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Attacks and Defenses Against LLM Fingerprinting
  2. 2025FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing
  3. 2026Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
  4. 2025Fingerprinting LLMs via Prompt Injection
  5. 2026A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors
  6. 2025EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint
  7. 2024LLMmap: Fingerprinting For Large Language Models
  8. 2025ImF: Implicit Fingerprint for Large Language Models