Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks
@article{Behnia2020CodeBridgedC, title={Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks}, author={F. Behnia and Ali Mirzaeian and M. Sabokrou and S. Manoj and T. Mohsenin and Khaled N. Khasawneh and Liang Zhao and H. Homayoun and Avesta Sasan}, journal={2020 21st International Symposium on Quality Electronic Design (ISQED)}, year={2020}, pages={27-32} }
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity. More specifically, we propose a stacked encoder-convolutional model, in which the input image is first encoded by the encoder module of a denoising auto-encoder, and then the resulting latent representation (without being decoded) is fed to a reduced… CONTINUE READING
Figures, Tables, and Topics from this paper
4 Citations
CSCMAC - Cyclic Sparsely Connected Neural Network Manycore Accelerator
- Computer Science
- 2020 21st International Symposium on Quality Electronic Design (ISQED)
- 2020
- 2
- PDF
Using Transfer Learning Approach to Implement Convolutional Neural Network model to Recommend Airline Tickets by Using Online Reviews
- Computer Science
- 2020 15th International Workshop on Semantic and Social Media Adaptation and Personalization (SMA
- 2020
- 4
Using BERT to Extract Topic-Independent Sentiment Features for Social Media Bot Detection
- 2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)
- 2020
- 4
Learning Diverse Latent Representations for Improving the Resilience to Adversarial Attacks
- Computer Science, Engineering
- ArXiv
- 2020
- 1
References
SHOWING 1-10 OF 32 REFERENCES
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 1,970
- Highly Influential
- PDF
Universal Adversarial Perturbations
- Computer Science, Mathematics
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 1,059
- PDF
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
- Computer Science, Mathematics
- AAAI
- 2018
- 232
- PDF
Going deeper with convolutions
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 21,878
- PDF
MagNet: A Two-Pronged Defense against Adversarial Examples
- Computer Science
- CCS
- 2017
- 533
- Highly Influential
- PDF
Towards Evaluating the Robustness of Neural Networks
- Computer Science
- 2017 IEEE Symposium on Security and Privacy (SP)
- 2017
- 2,943
- Highly Influential
- PDF
Boosting Adversarial Attacks with Momentum
- Computer Science
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 608
- Highly Influential
- PDF
Explaining and Harnessing Adversarial Examples
- Computer Science, Mathematics
- ICLR
- 2015
- 6,259
- Highly Influential
- PDF