mlsanityData to 7 Oct 2026

Deep Intellectual Property Protection: A Survey

arXiv 2304.14613 ↗First posted 28 Apr 2023cs.AI cs.CRcited by 16

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

Abstract (arXiv)

Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields. The high performance of DNNs requires a huge amount of high-quality data, expensive computing hardware, and excellent DNN architectures that are costly to obtain. Therefore, trained DNNs are becoming valuable assets and must be considered the Intellectual Property (IP) of the legitimate owner who created them, in order to protect trained DNN models from illegal reproduction, stealing, redistribution, or abuse. Although being a new emerging and interdisciplinary field, numerous DNN model IP protection methods have been proposed. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of two mainstream DNN IP protection methods: deep watermarking and deep fingerprinting, with a proposed taxonomy. More than 190 research contributions are included in this survey, covering many aspects of Deep IP Protection: problem definition, main threats and challenges, merits and demerits of deep watermarking and deep fingerprinting methods, evaluation metrics, and performance discussion. We finish the survey by identifying promising directions for future research.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 20 of its 231 references that are in the map. First posted on arXiv 28 Apr 2023.

Builds on

20 of 231 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Protecting Language Generation Models via Invisible Watermarking6 Feb
  2. 2023A Watermark for Large Language Models24 Jan
  3. 2022Distillation-Resistant Watermarking for Model Protection in NLP7 Oct

Other references · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2014Conditional Generative Adversarial Netscited by 2,152
  4. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  5. 2017A Review on Deep Learning Techniques Applied to Semantic Segmentationcited by 122
  6. 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
  7. 2019BlackMarks: Blackbox Multibit Watermarking for Deep Neural Networkscited by 25
  8. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 25
  9. 2022MOVE: Effective and Harmless Ownership Verification via Embedded External Featurescited by 20
  10. 2019Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarkingcited by 11
  11. 2019DeepSmartFuzzer: Reward Guided Test Generation For Deep Learningcited by 7
  12. 2021Protecting Your NLG Models with Semantic and Robust Watermarkscited by 7
5 more
  1. 2018Performance Comparison of Contemporary DNN Watermarking Techniquescited by 4
  2. 2019Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inferencecited by 4
  3. 2021Fingerprinting Multi-exit Deep Neural Network Models via Inference Timecited by 4
  4. 2022AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learningcited by 4
  5. 2021Fingerprinting Image-to-Image Generative Adversarial Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 10; 2026: 4.

16 papers.

Sort:

By area:

  1. 2025DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillationcited by 14
  2. 2023Wide Flat Minimum Watermarking for Robust Ownership Verification of GANscited by 10
  3. 2025FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprintcited by 8
  4. 2025DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protectioncited by 8
  5. 2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
  6. 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directionscited by 4
  7. 2026CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attackscited by 4
  8. 2025Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarkingcited by 2
  9. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 2
  10. 2025Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signaturescited by 2
  11. 2025Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulationcited by 1
  12. 2025WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networkscited by 1
4 more
  1. 2025Protecting Intellectual Property of EEG-based Neural Networks with Watermarkingcited by 0
  2. 2026SpanKey: Dynamic Key Space Conditioning for Neural Network Access Controlcited by 0
  3. 2026ADS-C: Antidistillation Sampling for Classificationcited by 0
  4. 2026TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Modelscited by 0