mlsanityData to 7 Oct 2026

HODA: Hardness-Oriented Detection of Model Extraction Attacks

arXiv 2106.11424 ↗First posted 21 Jun 2021cs.LG cs.CRcited by 2

Not on the map. Why?

Abstract (arXiv)

Model Extraction attacks exploit the target model's prediction API to create a surrogate model in order to steal or reconnoiter the functionality of the target model in the black-box setting. Several recent studies have shown that a data-limited adversary who has no or limited access to the samples from the target model's training data distribution can use synthesis or semantically similar samples to conduct model extraction attacks. In this paper, we define the hardness degree of a sample using the concept of learning difficulty. The hardness degree of a sample depends on the epoch number that the predicted label of that sample converges. We investigate the hardness degree of samples and demonstrate that the hardness degree histogram of a data-limited adversary's sample sequences is distinguishable from the hardness degree histogram of benign users' samples sequences. We propose Hardness-Oriented Detection Approach (HODA) to detect the sample sequences of model extraction attacks. The results demonstrate that HODA can detect the sample sequences of model extraction attacks with a high success rate by only monitoring 100 samples of them, and it outperforms all previous model extraction detection methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 41 of its 64 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

41 of 64 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  12. 2016Practical Black-Box Attacks against Machine Learningcited by 893
29 more
  1. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
  2. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  3. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  4. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  5. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  6. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
  7. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  8. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  9. 2021Deep Learning Through the Lens of Example Difficultycited by 139
  10. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 136
  11. 2020Data-Free Model Extractioncited by 121
  12. 2018Stealing Hyperparameters in Machine Learningcited by 115
  13. 2020Stealing Links from Graph Neural Networkscited by 114
  14. 2020MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimationcited by 99
  15. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 94
  16. 2020Characterizing Structural Regularities of Labeled Data in Overparameterized Modelscited by 93
  17. 2018Exploring Connections Between Active Learning and Model Extractioncited by 84
  18. 2019Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attackscited by 79
  19. 2018Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Datacited by 69
  20. 2018Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architecturescited by 56
  21. 2019Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasetscited by 55
  22. 2019Defending Against Model Stealing Attacks with Adaptive Misinformationcited by 55
  23. 2020Hermes Attack: Steal DNN Models with Lossless Inference Accuracycited by 41
  24. 2017Model Extraction Warning in MLaaS Paradigmcited by 39
  25. 2020Black-Box Ripper: Copying black-box models using generative evolutionary algorithmscited by 26
  26. 2020Stealing Deep Reinforcement Learning Models for Fun and Profitcited by 24
  27. 2019Extraction of Complex DNN Models: Real Threat or Boogeyman?cited by 19
  28. 2018Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attackscited by 18
  29. 2021When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statisticscited by 11

Built on by

Cited by year (2026 to 7 Oct)

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

2 papers.

  1. 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
  2. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1