基于KNN最小范化系数攻击在CNN上的利用
摘要
关键词
全文:
PDF参考
[1]C. Sitawarin and D. Wagner, “On the robustness of deep k- nearest neighbors,” vol. abs/1903.08333, 2019. [Online]. Available: http://arxiv.org/abs/1903.08333.
[2]Y. Yang, C. Rashtchian, Y. Wang, and K. Chaudhuri, “Adversarial examples for non-parametric methods: Attacks, defenses and large sample limits,” CoRR, vol. abs/1906.03310, 2019. [Online]. Available: http://arxiv.org/abs/1906.03310.
[3] W. Gao, X. Niu, and Z. Zhou, “On the consistency of exact and approximate nearest neighbor with noisy data,” CoRR, vol. abs/1607.07526, 2016. [Online]. Available: http://arxiv.org/ abs/1607.07526. [4] H. W. J. Reeve and A. Kab´an, “Fast rates for a knn classi-
fier robust to unknown asymmetric label noise,” CoRR, vol. abs/1906.04542, 2019. [Online]. Available: http://arxiv.org/ abs/1906.04542.
[5] Christian Szegedy. Wojciech Zaremba. Ilya Sutskever. Joan Bru-na. Dumitru Erhan. Ian J. Goodfellow. and Rob Fergus. Intriguing properties of neural networks. In ICLR, 2014.
[6] C. Sitawarin and D. Wagner, “Minimum-Norm Adversarial Ex- amples on KNN and KNN-Based Models,” vol. abs/2003.06559, 2019. [Online]. Available: http://arxiv.org/abs/2003.06559.
DOI: http://dx.doi.org/10.18686/jsjxt.v2i3.30186
Refbacks
- 当前没有refback。