Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn 07-12-June-2015, Issue , 2015, Pages 427-436

  Nguyen, Anh ^a   Yosinski, Jason ^b   Clune, Jeff ^a  

^a UNIVERSITY OF WYOMING   (United States)

^b Department of Molecular Biology and Genetics   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER VISION; NEURAL NETWORKS; WHITE NOISE;

CONVOLUTIONAL NEURAL NETWORK; DEEP NEURAL NETWORKS; GRADIENT ASCENT; HIGH CONFIDENCE; HUMAN-LEVEL PERFORMANCE; STATE OF THE ART; STATE-OF-THE-ART PERFORMANCE; VISUAL CLASSIFICATION;

PATTERN RECOGNITION;

EID: 84946206172     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CVPR.2015.7298640     Document Type: Conference Paper

References (32)

1. J. E. Auerbach. Automated evolution of interesting images. In Artificial Life 13, number EPFL-CONF-191282. MIT Press, 2012
2. Y. Bengio. Learning deep architectures for ai. Foundations and trends in Machine Learning, 2(1):1-127, 2009
3. Y. Bengio, E. Thibodeau-Laufer, G. Alain, and J. Yosinski. Deep generative stochastic networks trainable by backprop. In Proceedings of the 30th International Conference on Machine Learning, 2014
4. I. Biederman. Visual object recognition, volume 2. MIT press Cambridge, 1995
5. J. Clune, K. Stanley, R. Pennock, and C. Of ria. On the performance of indirect encoding across the continuum of regularity. IEEE Transactions on Evolutionary Computation, 15(4):346-367, 2011
6. A. Cully, J. Clune, and 1.-B. Mouret. Robots that can adapt like natural animals. arXiv preprint arXiv:I407. 350I, 2014
7. G. E. Dahl, D. Yu, L. Deng, and A. Acero. Contextdependent pre-trained deep neural networks for 1argevocabulary speech recognition. Audio, Speech, and Language Processing, IEEE Transactions on, 20(1):30-42, 2012
8. K. Deb. Multi-objective optimization using evolutionary algorithms, volume 16. John Wiley & Sons, 2001
9. J. Deng,A. Berg, S. Satheesh, H. Su,A. Khosla, and L. FeiFei. Imagenet large scale visual recognition competition 2012 (ilsvrc2012), 2012
10. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. FeiFei. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 248-255. IEEE, 2009
11. D. Erhan, Y. Bengio, A. Courville, and P. Vincent. Visualizing higher-layer features of a deep network. Dept. IRO, Universite de Montreal, Tech. Rep, 2009
12. D. Floreano and C. Mattiussi. Bio-inspired artificial intelligence: theories, methods, and technologies. MIT press, 2008
13. I. J. Goodfellow, J. Sh1ens, and C. Szegedy. Explaining and harnessing adversaria1 examples. arXiv preprint arXiv:I412. 6572, Dec. 2014
14. G. E. Hinton. Learning multiple layers of representation. Trends in cognitive sciences, 11(10):428-434, 2007
15. Y. Lia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:I408. 5093, 2014
16. A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097-1105, 2012
17. Q. V. Le, W. Y. Zou, S. Y. Yeung, and A. Y. Ng. Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 3361-3368. IEEE, 2011
18. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradientbased learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998
19. Y. LeCun and C. Cortes. The mnist database of handwritten digits, 1998
20. H. Lipson. Principles of modularity, regularity, and hierarchy for scalable systems. Journal of Biological Physics and Chemistry, 7(4):125, 2007
21. J.-B. Mouret and S. Doncieux. Sferes v2: Evo1vin'in the multi-core world. In Evolutionary Computation (CEC), 2010 IEEE Congress on, pages 4079-4086. IEEE, 2010
22. V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-1O), pages 807-814, 2010
23. A. Nguyen, J. Yosinski, and J. Clune. Introducing the innovation engine:A utomated creativity and improved stochastic optimization via deep learning. In Proceedings of the Genetic and Evolutionary Computation Conference, 2015
24. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. Imagenet large scale visual recognition challenge. arXiv preprint arXiv: 1409. 0575, 2014
25. J. Secretan, N. Beato, D. B. DAmbrosio, A. Rodriguez, A. Campbell, and K. O. Stanley. Picbreeder: evolving pictures collaboratively online. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 1759-l768. ACM, 2008
26. K. Simonyan, A. Vedaldi, and A. Zisserman. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:13I2. 6034, 2013
27. K. Stanley and R. Miikkulainen. Evolving neural networks through augmenting topologies. Evolutionary computation, 10(2):99-127, 2002
28. K. O. Stanley. Compositional pattern producing networks: A novel abstraction of development. Genetic programming and evolvable machines, 8(2):131-162, 2007
29. K. O. Stanley and R. Miikku1ainen. A taxonomy for artificial embryogeny. Artificial Life, 9(2):93-130, 2003
30. c. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus. Intriguing properties of neural networks. arXiv preprint arXiv:13I2. 6I99, 2013
31. Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages l701-l708. IEEE, 2014
32. J. Yosinski, J. Clune, Y. Bengio, and H. Lipson. How transferable are features in deep neural networks? In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Weinberger, editors, Advances in Neural Information Processing Systems 27, pages 3320-3328. CurranA ssociates, Inc., Dec. 2014.