“第十九章 深度学习的问题”版本间的差异
来自cslt Wiki
| 第12行： | 第12行： | ||
* 知乎：可解释人工智能[https://zhuanlan.zhihu.com/p/354233093] | * 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] | * 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== | ||
| 第22行： | 第22行： | ||
==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== | ||
2022年8月8日 (一) 06:52的版本
教学资料
扩展阅读
视频展示
演示链接
开发者资源
- AI安全之对抗样本入门 [6]
高级读者
- What is adversarial machine learning [7]
- 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. [8]
- Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks[J]. arXiv preprint arXiv:1312.6199, 2013. [9]
- 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. [10]
- 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. [11]
- 可解释人工智能导论 [12]
