Adversarial-ML-Papers

This note contains links to current papers in adversarial machine learning research.

Papers:

1. Dimensionality Reduction viewpoint:
   1. PCA Whitening: https://openreview.net/pdf?id=B1dexpDug
   2. PCA + others : https://arxiv.org/pdf/1704.02654.pdf
   3. Feature Squeezing: https://arxiv.org/pdf/1704.01155.pdf
2. Subspace viewpoint: https://arxiv.org/pdf/1704.03453.pdf
3. Theoretical Viewpoint (risk and difference in class means): https://arxiv.org/pdf/1502.02590.pdf
4. Hidden Space Viewpoint:
   1. Hidden Space Traversal viewpoint: https://arxiv.org/pdf/1511.06421.pdf
   2. Hidden Space manipulation viewpoint: https://arxiv.org/pdf/1511.05122.pdf
   3. Inverting Represenations (supplements the above two): https://www.robots.ox.ac.uk/~vedaldi/assets/pubs/mahendran15understanding.pdf

Background reading on Adversarial Machine Learning Research: https://github.com/yenchenlin/awesome-adversarial-machine-learning