PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
Not on the map. Why?
Abstract (arXiv)
Adversarial extraction attacks constitute an insidious threat against Deep Learning (DL) models in-which an adversary aims to steal the architecture, parameters, and hyper-parameters of a targeted DL model. Existing extraction attack literature have observed varying levels of attack success for different DL models and datasets, yet the underlying cause(s) behind their susceptibility often remain unclear, and would help facilitate creating secure DL systems. In this paper we present PINCH: an efficient and automated extraction attack framework capable of designing, deploying, and analyzing extraction attack scenarios across heterogeneous hardware platforms. Using PINCH, we perform extensive experimental evaluation of extraction attacks against 21 model architectures to explore new extraction attack scenarios and further attack staging. Our findings show (1) key extraction characteristics whereby particular model configurations exhibit strong resilience against specific attacks, (2) even partial extraction success enables further staging for other adversarial attacks, and (3) equivalent stolen models uncover differences in expressive power, yet exhibit similar captured knowledge.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 72 references that are in the map. First posted on arXiv 13 Sep 2022.
Builds on
36 of 72 references.
References · 36
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2022A ConvNet for the 2020scited by 3,545
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
- 2019A Comprehensive Survey on Transfer Learningcited by 1,154
- 2020Designing Network Design Spacescited by 954
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2017Evasion Attacks against Machine Learning at Test Timecited by 686
- 2016Stealing Machine Learning Models via Prediction APIscited by 602
24 more
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
- 2018Insights on representational similarity in neural networks with canonical correlationcited by 318
- 2017Adversarial Attacks on Neural Network Policiescited by 314
- 2016On the Expressive Power of Deep Neural Networkscited by 302
- 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
- 2018Adversarial Attacks and Defences: A Surveycited by 259
- 2018Adversarial Robustness Toolbox v1.0.0cited by 214
- 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 208
- 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
- 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 147
- 2018Stealing Hyperparameters in Machine Learningcited by 115
- 2018Exploring Connections Between Active Learning and Model Extractioncited by 84
- 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 79
- 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
- 2017Natasha 2: Faster Non-Convex Optimization Than SGDcited by 49
- 2015From Facial Parts Responses to Face Detection: A Deep Learning Approachcited by 42
- 2018Stealing Neural Networks via Timing Side Channelscited by 42
- 2020Hermes Attack: Steal DNN Models with Lossless Inference Accuracycited by 41
- 2018A Frank-Wolfe Framework for Efficient and Effective Adversarial Attackscited by 29
- 2020ES Attack: Model Stealing against Deep Neural Networks without Data Hurdlescited by 24
- 2018Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attackscited by 18
- 2021AI Accelerator Survey and Trendscited by 17
- 2019Spectral Metric for Dataset Complexity Assessmentcited by 15
Built on by
Citing papers per year: 2023: 2.
2 papers.