mlsanityData to 14 Oct 2026

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection

arXiv 2601.08223 ↗First posted 13 Jan 2026cs.CR cs.AIcited by 0

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs susceptible to filtering -- or use fixed trigger-response mappings that are brittle to leakage and post-hoc adaptation. We propose textscDual-Layer Nested Fingerprinting (DNF), a black-box method that embeds a hierarchical backdoor by coupling domain-specific stylistic cues with implicit semantic triggers. Across Mistral-7B, LLaMA-3-8B-Instruct, and Falcon3-7B-Instruct, DNF achieves perfect fingerprint activation while preserving downstream utility. Compared with existing methods, it uses lower-perplexity triggers, remains undetectable under fingerprint detection attacks, and is relatively robust to incremental fine-tuning and model merging. These results position DNF as a practical, stealthy, and resilient solution for LLM ownership verification and intellectual property protection.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 34 of its 46 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

34 of 46 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor5 Sep
  2. 2025Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends15 Aug
  3. 2024Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition13 Sep
  4. 2024Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging8 Apr
  5. 2024Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning22 Feb
  6. 2021Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models10 Dec

Other references · 28

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Mistral 7Bcited by 3,164
  3. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  4. 2018Neural Network Acceptability Judgmentscited by 958
  5. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 839
  6. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  7. 2024Arcee's MergeKit: A Toolkit for Merging Large Language Modelscited by 194
  8. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 108
  9. 2024Instructional Fingerprinting of Large Language Modelscited by 68
  10. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 58
  11. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  12. 2024Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoningcited by 50
16 more
  1. 2024Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Techniquecited by 37
  2. 2024REEF: Representation Encoding Fingerprints for Large Language Modelscited by 36
  3. 2023HuRef: HUman-REadable Fingerprint for Large Language Modelscited by 34
  4. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Modelscited by 34
  5. 2024A Fingerprint for Large Language Modelscited by 28
  6. 2024UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identificationcited by 18
  7. 2025RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliabilitycited by 14
  8. 2025Cost-Effective Communication: An Auction-based Method for Language Agent Interactioncited by 14
  9. 2025IAG: Input-aware Backdoor Attack on VLM-based Visual Groundingcited by 12
  10. 2025EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprintcited by 12
  11. 2025PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancementcited by 11
  12. 2025Web Fraud Attacks Against LLM-Driven Multi-Agent Systemscited by 10
  13. 2025Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?cited by 10
  14. 2025SRAF: Stealthy and Robust Adversarial Fingerprint for Copyright Verification of Large Language Modelscited by 8
  15. 2025Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Modelscited by 8
  16. 2025ImF: Implicit Fingerprint for Large Language Modelscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection
  2. 2026A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors
  3. 2026SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models
  4. 2025SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting
  5. 2025FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing
  6. 2026From Bits to Beliefs: Recoverable Semantic Fingerprints for Black-Box Verification of Large Language Models
  7. 2025iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification
  8. 2026KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing ↗