“第十九章 深度学习的问题”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(相同用户的2个中间修订版本未显示)
第9行: 第9行:
 
==扩展阅读==
 
==扩展阅读==
  
 
+
* 维基百科:可解释人工智能[http://aigraph.cslt.org/courses/19/Explainable_artificial_intelligence.pdf][http://aigraph.cslt.org/courses/19/可解釋人工智慧.pdf]
 +
* 知乎:可解释人工智能[https://zhuanlan.zhihu.com/p/354233093]
 +
* 脆弱的神经网络:UC Berkeley详解对抗样本生成机制 [https://www.jiqizhixin.com/articles/2018-01-31-5]
 +
* 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 [https://cloud.tencent.com/developer/article/1418617]
  
 
==视频展示==
 
==视频展示==
  
 +
* Deep neural networks are easy to fool [http://aigraph.cslt.org/courses/19/easy-fool.mp4]
  
 
==演示链接==
 
==演示链接==
 
+
* Demo of adversarial attack [https://kennysong.github.io/adversarial.js/]
  
 
==开发者资源==
 
==开发者资源==
  
 +
* AI安全之对抗样本入门 [https://github.com/duoergun0729/adversarial_examples]
  
 
==高级读者==
 
==高级读者==
第26行: 第31行:
 
* 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. [https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Nguyen_Deep_Neural_Networks_2015_CVPR_paper.pdf]
 
* 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. [https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Nguyen_Deep_Neural_Networks_2015_CVPR_paper.pdf]
 
* 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. [http://openaccess.thecvf.com/content_cvpr_2018/papers/Eykholt_Robust_Physical-World_Attacks_CVPR_2018_paper.pdf]
 
* 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. [http://openaccess.thecvf.com/content_cvpr_2018/papers/Eykholt_Robust_Physical-World_Attacks_CVPR_2018_paper.pdf]
 +
* 可解释人工智能导论 [https://item.jd.com/13700578.html]

2022年8月8日 (一) 07:16的最后版本


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]