第十九章 深度学习的问题

来自cslt Wiki
跳转至: 导航搜索


教学资料


扩展阅读

  • 维基百科:可解释人工智能[1][2]
  • 知乎:可解释人工智能[3]
  • 脆弱的神经网络:UC Berkeley详解对抗样本生成机制 [4]
  • 对抗样本为什么重要:未解决的研究问题与真实的威胁模型 [5]

视频展示

  • Deep neural networks are easy to fool [6]

演示链接

  • Demo of adversarial attack [7]

开发者资源

  • AI安全之对抗样本入门 [8]

高级读者

  • What is adversarial machine learning [9]
  • Fong R C, Vedaldi A. Interpretable explanations of black boxes by meaningful perturbation[C]//Proceedings of the IEEE international conference on computer vision. 2017: 3429-3437. [10]
  • Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks[J]. arXiv preprint arXiv:1312.6199, 2013. [11]
  • Nguyen A, Yosinski J, Clune J. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 427-436. [12]
  • Eykholt K, Evtimov I, Fernandes E, et al. Robust physical-world attacks on deep learning visual classification[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 1625-1634. [13]
  • 可解释人工智能导论 [14]