Vir Virander Phoha

Safety, Robustness & Interpretability · 2016

A researcher in the Science corpus: 1 paper; trusts 16 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Safety, Robustness & Interpretability — 9 citations into it
• Artificial Intelligence — 8 citations into it
• Computer Networks and Communications — 6 citations into it
• Signal Processing — 6 citations into it

Whom Vir Virander Phoha trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Battista Biggio
2. Yann LeCun
3. Corinna Cortes
4. Han Xiao
5. Blaine Nelson
6. Martin Ester
7. Michael Brückner
8. Marco Barreno

Papers from Vir Virander Phoha's perspective

Ordered by how strongly the researchers Vir Virander Phoha trusts endorse each paper. Same corpus, a different order for every researcher.

1. Support-Vector Networks
2. The security of machine learning
3. Static prediction games for adversarial learning problems
4. Can machine learning be secure?
5. ImageNet classification with deep convolutional neural networks
6. Adversarial classification
7. Gradient-based learning applied to document recognition
8. Stackelberg games for adversarial prediction problems
9. The mnist database of handwritten digits
10. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)

Their papers

• Curie: A method for protecting SVM Classifier from Poisoning Attack (2016) — 54 citations