Sparsity-based Defense Against Adversarial Attacks on Linear Classifiers
作者： Zhinus Marzi , Soorya Gopalakrishnan , Upamanyu Madhow , Ramtin Pedarsani
DOI: 10.1109/ISIT.2018.8437638
关键词:
摘要: Deep neural networks represent the state of the art in machine learning in a growing number of fields, including vision, speech and natural language processing. However, recent work …
sci-hub.se 
arxiv.org 参考文章(11)
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard, DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks computer vision and pattern recognition. pp. 2574- 2582 ,(2016) , 10.1109/CVPR.2016.282
Duen Horng Chau, Li Chen, Shang-Tse Chen, Fred Hohman, Madhuri Shanbhogue, Nilaksh Das, Michael E. Kounavis, Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression arXiv: Computer Vision and Pattern Recognition. ,(2017)
Daniel Cullina, Prateek Mittal, Arjun Nitin Bhagoji, Dimensionality Reduction as a Defense against Evasion Attacks on Machine Learning Classifiers. ,(2017)
Stefano Soatto, Pascal Frossard, Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Classification regions of deep neural networks arXiv: Computer Vision and Pattern Recognition. ,(2017)
Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, The Robustness of Deep Networks: A Geometrical Perspective IEEE Signal Processing Magazine. ,vol. 34, pp. 50- 62 ,(2017) , 10.1109/MSP.2017.2740965
Brendan Frey, Alireza Makhzani, k-Sparse Autoencoders international conference on learning representations. ,(2014)
Ian J Goodfellow, Jonathon Shlens, Christian Szegedy, None, Explaining and Harnessing Adversarial Examples international conference on learning representations. ,(2015)
Ben Poole, Surya Ganguli, Maithreyi Raghu, Subhaneil Lahiri, Jascha Sohl-Dickstein, Exponential expressivity in deep neural networks through transient chaos neural information processing systems. ,vol. 29, pp. 3360- 3368 ,(2016)
Ilya Sutskever, Christian Szegedy, Ian Goodfellow, Joan Bruna, Rob Fergus, Rob Fergus, Dumitru Erhan, Wojciech Zaremba, Intriguing properties of neural networks international conference on learning representations. ,(2014)