mlsanityData to 14 Oct 2026

LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains

arXiv 2606.17123 ↗First posted 15 Jun 2026cs.CR cs.AIcited by 0

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

Abstract (arXiv)

In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains. Consequently, tracking and verifying historical contributions is essential for model provenance and intellectual property protection. However, existing watermarking methods are mainly designed for single-user, one-time embeddings, often fail under repeated model derivation and incremental updates. To address this problem, we propose LineageMark, a multi-user white-box watermarking framework for model derivation chains. The framework encodes watermarks in model parameters using a projection-based approach. Stable carriers are first selected to reduce sensitivity to model changes, each watermark bit is then represented as a projection statistic over these carriers. Additional watermark insertions introduce only bounded perturbations in the projection space, and margin constraints are used to maintain signal integrity. We evaluate the effectiveness of LineageMark in multi-stage model derivation chains. Experimental results show that LineageMark preserves contributor watermarks across multi-stage derivation and supports incremental multi-user watermark insertion. Furthermore, it exhibits robustness against perturbations such as re-watermarking, fine-tuning, quantization, and pruning.

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 38 of its 51 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

38 of 51 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models27 Feb
  2. 2024Watermarking Makes Language Models Radioactive22 Feb
  3. 2023Robust Distortion-free Watermarks for Language Models28 Jul
  4. 2023On the Reliability of Watermarks for Large Language Models7 Jun
  5. 2023Undetectable Watermarks for Language Models25 May
  6. 2023A Watermark for Large Language Models24 Jan

Other references · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  5. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  8. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  9. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  10. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  11. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  12. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
20 more
  1. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  2. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  3. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
  4. 2022Editing Models with Task Arithmeticcited by 1,120
  5. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  6. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  7. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 818
  8. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 735
  9. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  10. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  11. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 543
  12. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  13. 2021When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Datasetcited by 201
  14. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 148
  15. 2019Large-Scale Multi-Label Text Classification on EU Legislationcited by 104
  16. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 100
  17. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 88
  18. 2021Proof-of-Learning: Definitions and Practicecited by 84
  19. 2024Instructional Fingerprinting of Large Language Modelscited by 68
  20. 2024MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Modelscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SEAL: Subspace-Anchored Watermarks for LLM Ownership
  2. 2024Watermarking Language Models through Language Models
  3. 2025PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
  4. 2024A Watermark for Black-Box Language Models
  5. 2023Unbiased Watermark for Large Language Models
  6. 2025StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
  7. 2025Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
  8. 2024WAPITI: A Watermark for Finetuned Open-Source LLMs