DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation

This paper investigates the piracy problem of deep learning models. Designing and training a well-performing model is generally expensive. However, when releasing them, attackers may reverse engineer the models and pirate their design. This paper, therefore, proposes deep learning obfuscation, aiming at obstructing attackers from pirating a deep learning model. In particular, we focus on obfuscating convolutional neural networks (CNN), a widely employed type of deep learning architectures for image recognition. Our approach obfuscates a CNN model eventually by simulating its feature extractor with a shallow and sequential convolutional block. To this end, we employ a recursive simulation method and a joint training method to train the simulation network. The joint training method leverages both the intermediate knowledge generated by a feature extractor and data labels to train a simulation network. In this way, we can obtain an obfuscated model without accuracy loss. We have verified the feasibility of our approach with three prevalent CNNs, i.e., GoogLeNet, ResNet, and DenseNet. Although these networks are very deep with tens or hundreds of layers, we can simulate them in a shallow network including only five or seven convolutional layers. The obfuscated models are even more efficient than the original models. Our obfuscation approach is very effective to protect the critical structure of a deep learning model from being exposed to attackers. Moreover, it can also thwart attackers from pirating the model with transfer learning or incremental learning techniques because the shallow simulation network bears poor learning ability. To our best knowledge, this paper serves as a first attempt to obfuscate deep learning models, which may shed light on more future studies.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[3]  Christian S. Collberg,et al.  Toward Digital Asset Protection , 2011, IEEE Intelligent Systems.

[4]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[6]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yoshua Bengio,et al.  FitNets: Hints for Thin Deep Nets , 2014, ICLR.

[8]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Junfeng Yang,et al.  DeepXplore , 2019, Commun. ACM.

[10]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[11]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Yuxin Peng,et al.  Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification , 2014, ACM Multimedia.

[14]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[15]  Christian S. Collberg,et al.  A Taxonomy of Obfuscating Transformations , 1997 .

[16]  Nicholas D. Lane,et al.  DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices , 2016, 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[17]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Giuseppe Ateniese,et al.  Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning , 2017, CCS.

[20]  Fan Zhang,et al.  Stealing Machine Learning Models via Prediction APIs , 2016, USENIX Security Symposium.

[21]  Jian Cheng,et al.  Accelerating Convolutional Neural Networks for Mobile Applications , 2016, ACM Multimedia.

[22]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[23]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[24]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[25]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[26]  Ananthram Swami,et al.  Practical Black-Box Attacks against Machine Learning , 2016, AsiaCCS.

[27]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.