Adversarial manipulation of deep representations

4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings

Volumn , Issue , 2016, Pages

  Sabour, Sara ^a   Cao, Yanshuai ^a,b   Faghri, Fartash ^a,b   Fleet, David J ^a  

^a UNIVERSITY OF TORONTO   (Canada)

^b Architech Labs   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

CLASS LABELS; DIFFERENT CLASS; IMAGE REPRESENTATIONS; INTERNAL LAYERS; INTERNAL REPRESENTATION; NATURAL IMAGES; ORIGINAL IMAGES;

DEEP NEURAL NETWORKS;

EID: 85083951731     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Chatfield, K., Simonyan, K., Vedaldi, A., and Zisserman, A. Return of the devil in the details: Delving deep into convolutional nets. In BMVC, 2014. 3, 6
2. Deng, J, Dong, W, Socher, R, Li, LJ, Li, K, and Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In IEEE CVPR, pp. 248–255, 2009. 3
3. Fawzi, A, Fawzi, O, and Frossard, P. Fundamental limits on adversarial robustness. In ICML, 2015. 1, 2
4. Glorot, X, Bordes, A, and Bengio, Y. Deep sparse rectifier neural networks. In AISTATS, volume 15, pp. 315–323, 2011. 7
5. Goodfellow, IJ, Shlens, J, and Szegedy, C. Explaining and harnessing adversarial examples. In ICLR (arXiv:1412.6572), 2014. 1, 2, 7, 8, 11
6. Gu, S and Rigazio, L. Towards deep neural network architectures robust to adversarial examples. In Deep Learning and Representation Learning Workshop (arXiv:1412.5068), 2014. 1
7. Jia, Y, Shelhamer, E, Donahue, J, Karayev, S, Long, J, Girshick, R, Guadarrama, S, and Darrell, T. Caffe: Convolutional architecture for fast feature embedding. In ACM Int. Conf. Multimedia, pp. 675–678, 2014. 2, 6
8. Krizhevsky, A, Sutskever, I, and Hinton, GE. Imagenet classification with deep convolutional neural networks. In NIPS, pp. 1097–1105, 2012. 3, 6
9. Mahendran, A and Vedaldi, A. Understanding deep image representations by inverting them. In IEEE CVPR (arXiv:1412.0035), 2014. 3, 4
10. Nguyen, A, Yosinski, J, and Clune, J. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In IEEE CVPR (arXiv:1412.1897), 2015. 1, 2
11. Szegedy, C, Zaremba, W, Sutskever, I, Bruna, J, Erhan, D, Goodfellow, I, and Fergus, R. Intriguing properties of neural networks. In ICLR (arXiv:1312.6199), 2014. 1, 2, 3, 7
12. Szegedy, C, Liu, W, Jia, Y, Sermanet, P, Reed, S, Anguelov, D, Erhan, D, Vanhoucke, V, and Rabi-novich, A. Going deeper with convolutions. In CVPR, 2015. 3, 6
13. Tabacof, P and Valle, E. Exploring the space of adversarial images. arXiv preprint arXiv:1510.05328, 2015. 1
14. Wang, Z, Bovik, AC, Sheikh, HR, and Simoncelli, EP. Image quality assessment: From error visibility to structural similarity. IEEE Trans. PAMI, 3(4):600–612, 2004. 2
15. Zhou, B, Lapedriza, A, Xiao, J, Torralba, A, and Oliva, A. Learning deep features for scene recognition using places database. In NIPS, pp. 487–495, 2014. 3, 6