Marco Barreno

Computer Networks and Communications · 2006–2010

A researcher in the Science corpus: 5 papers; trusts 7 researchers and is trusted by 79 researchers here, as inferred from the citation graph.

Subfields

• Computer Networks and Communications — 42 citations into it; #292 of 9,886 by trust here, #138 by citations
• Artificial Intelligence — 33 citations into it; #6,513 of 35,345 by trust here, #4,190 by citations
• Information Systems — 27 citations into it; #849 of 8,771 by trust here, #427 by citations
• Safety, Robustness & Interpretability — 27 citations into it; #148 of 2,251 by trust here, #147 by citations
• Signal Processing — 26 citations into it; #376 of 7,572 by trust here, #212 by citations
• Natural Language Processing — 14 citations into it
• Privacy & Security — 14 citations into it; #61 of 709 by trust here, #21 by citations

Whom Marco Barreno trusts overall

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

1. Daniel Lowd
2. James Newsome
3. Gordon V. Cormack
4. Tony Andrew Meyer
5. Bryan Klimt
6. Blaine Nelson
7. Christopher Meek
8. Michael Kearns
9. Leslie G. Valiant
10. Nilesh N. Dalvi

Who trusts Marco Barreno overall

1. Battista Biggio
2. Blaine Nelson
3. Nicolas Papernot
4. Fabio Roli
5. Nicholas Carlini
6. Davide Maiorca
7. Pavel Laskov
8. Ambra Demontis
9. Giorgio Fumera
10. Arturo Geigel

Papers from Marco Barreno's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Gradient-based learning applied to document recognition
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. A theory of the learnable
5. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
6. Attention is All you Need (Neural Information Processing Systems)
7. Long Short-Term Memory
8. On Attacking Statistical Spam Filters
9. Learning Multiple Layers of Features from Tiny Images
10. Adversarial learning

Their papers

• Can machine learning be secure? (2006) — 1,007 citations
• Open problems in the security of learning (2008) — 44 citations
• Misleading Learners: Co-opting Your Spam Filter (2009) — 125 citations
• The security of machine learning (2010) — 928 citations
• Exploiting Machine Learning to Subvert Your Spam Filter (2008) — 397 citations