mlsanityData to 7 Oct 2026

Model Extraction and Defenses on Generative Adversarial Networks

arXiv 2101.02069 ↗First posted 6 Jan 2021cs.CR cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success, model extraction attacks against generative models are less well explored. In this paper, we systematically study the feasibility of model extraction attacks against generative adversarial networks (GANs). Specifically, we first define accuracy and fidelity on model extraction attacks against GANs. Then we study model extraction attacks against GANs from the perspective of accuracy extraction and fidelity extraction, according to the adversary's goals and background knowledge. We further conduct a case study where an adversary can transfer knowledge of the extracted model which steals a state-of-the-art GAN trained with more than 3 million images to new domains to broaden the scope of applications of model extraction attacks. Finally, we propose effective defense techniques to safeguard GANs, considering a trade-off between the utility and security of GAN models.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 6 Jan 2021.

Builds on

56 of 76 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  10. 2016Improved Techniques for Training GANscited by 2,938
  11. 2016Deep Learning with Differential Privacycited by 2,682
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
38 more
  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  2. 2020Extracting Training Data from Large Language Modelscited by 2,144
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  10. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  11. 2019Passage Re-ranking with BERTcited by 629
  12. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  13. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  14. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  15. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  16. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  17. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  18. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  19. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  20. 2019Fixing the train-test resolution discrepancycited by 209
  21. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
  22. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  23. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  24. 2019Seeing What a GAN Cannot Generatecited by 148
  25. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  26. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 136
  27. 2019Fine-tune BERT for Extractive Summarizationcited by 122
  28. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  29. 2018Model Reconstruction from Model Explanationscited by 84
  30. 2018Exploring Connections Between Active Learning and Model Extractioncited by 84
  31. 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
  32. 2020Cryptanalytic Extraction of Neural Network Modelscited by 65
  33. 2018On GANs and GMMscited by 62
  34. 2019High-Fidelity Image Generation With Fewer Labelscited by 51
  35. 2018Discriminator Rejection Samplingcited by 48
  36. 2017TextureGAN: Controlling Deep Image Synthesis with Texture Patchescited by 47
  37. 2016Stacked Generative Adversarial Networkscited by 44
  38. 2018Metropolis-Hastings Generative Adversarial Networkscited by 40

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 3; 2025: 1; 2026: 1.

8 papers.

  1. 2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
  2. 2024DP-TLDM: Differentially Private Tabular Latent Diffusion Modelcited by 5
  3. 2021Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Modelscited by 3
  4. 2025Quantifying the Privacy Implications of High-Fidelity Synthetic Network Trafficcited by 3
  5. 2023Tokenized Model: A Blockchain-Empowered Decentralized Model Ownership Verification Platformcited by 0
  6. 2024Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Themcited by 0
  7. 2024Sequencing the Neurome: Towards Scalable Exact Parameter Reconstruction of Black-Box Neural Networkscited by 0
  8. 2026IP Protection in the Era of Visual Generative AI: A Surveycited by 0