mlsanityData to 7 Oct 2026

DREAM: Domain-free Reverse Engineering Attributes of Black-box Model

arXiv 2307.10997 ↗First posted 20 Jul 2023cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes (e.g., the number of convolutional layers) of a target black-box neural network can be exposed through a sequence of queries. There is a crucial limitation: these works assume the dataset used for training the target model to be known beforehand and leverage this dataset for model attribute attack. However, it is difficult to access the training dataset of the target black-box model in reality. Therefore, whether the attributes of a target black-box model could be still revealed in this case is doubtful. In this paper, we investigate a new problem of Domain-agnostic Reverse Engineering the Attributes of a black-box target Model, called DREAM, without requiring the availability of the target model's training dataset, and put forward a general and principled framework by casting this problem as an out of distribution (OOD) generalization problem. In this way, we can learn a domain-agnostic model to inversely infer the attributes of a target black-box model with unknown training data. This makes our method one of the kinds that can gracefully apply to an arbitrary domain for model attribute reverse engineering with strong generalization ability. Extensive experimental studies are conducted and the results validate the superiority of our proposed method over the baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 63 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

46 of 63 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  8. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  9. 2021Membership Inference Attacks From First Principlescited by 839
  10. 2021Domain Generalization: A Surveycited by 760
  11. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  12. 2021Domain Generalization with MixStylecited by 563
34 more
  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2020Label-Only Membership Inference Attackscited by 371
  3. 2020Environment Inference for Invariant Learningcited by 306
  4. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  5. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 262
  6. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  7. 2020Domain Generalization using Causal Matchingcited by 224
  8. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  9. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  10. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  11. 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
  12. 2020Data-Free Model Extractioncited by 121
  13. 2018Stealing Hyperparameters in Machine Learningcited by 115
  14. 2020MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimationcited by 99
  15. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  16. 2022Membership Inference Attacks by Exploiting Loss Trajectorycited by 93
  17. 2019Reverse-Engineering Deep ReLU Networkscited by 81
  18. 2019Stable Learning via Sample Reweightingcited by 70
  19. 2019Domain Generalization via Multidomain Discriminant Analysiscited by 69
  20. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
  21. 2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
  22. 2019Correlation-aware Adversarial Domain Adaptation and Generalizationcited by 65
  23. 2020Stable Prediction with Model Misspecification and Agnostic Distribution Shiftcited by 62
  24. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  25. 2022Towards Data-Free Model Stealing in a Hard Label Settingcited by 57
  26. 2018Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architecturescited by 56
  27. 2018Stable Prediction across Unknown Environmentscited by 55
  28. 2020Hermes Attack: Steal DNN Models with Lossless Inference Accuracycited by 41
  29. 2021TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systemscited by 36
  30. 2022Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoderscited by 30
  31. 2019Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentationcited by 29
  32. 2020Domain Generalization via Optimal Transport with Metric Similarity Learningcited by 27
  33. 2021Delving into Data: Effectively Substitute Training for Black-box Attackcited by 27
  34. 2022DST: Dynamic Substitute Training for Data-free Black-box Attackcited by 7

Built on by

Not cited yet.