Ambra Demontis

Safety, Robustness & Interpretability · 2016–2019

A researcher in the Science corpus: 8 papers; trusts 60 researchers and is trusted by 8 researchers here, as inferred from the citation graph.

Subfields

• Safety, Robustness & Interpretability — 157 citations into it; #908 of 2,251 by trust here, #660 by citations
• Artificial Intelligence — 156 citations into it; #12,613 of 35,345 by trust here, #7,112 by citations
• Signal Processing — 95 citations into it; #3,234 of 7,572 by trust here, #2,743 by citations
• Computer Networks and Communications — 76 citations into it; #6,103 of 9,886 by trust here, #6,217 by citations
• Information Systems — 41 citations into it
• Computer Vision and Pattern Recognition — 35 citations into it
• Privacy & Security — 30 citations into it; #641 of 709 by trust here, #586 by citations
• Optimization & Training — 16 citations into it

Whom Ambra Demontis trusts overall

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

1. Battista Biggio
2. Blaine Nelson
3. Fabio Roli
4. Giorgio Fumera
5. Yann LeCun
6. Geoffrey E. Hinton
7. L. Eon Bottou
8. Marco Barreno
9. Yoshua Bengio
10. Alex Krizhevsky

Who trusts Ambra Demontis overall

1. Battista Biggio
2. Marco Melis
3. Davide Maiorca
4. Fabio Roli
5. Giorgio Giacinto
6. Vale Tolpegin
7. Maura Pintor
8. Fabio Pierazzi
9. A. Serban
10. Matthew Jagielski

Papers from Ambra Demontis's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization (2017) — 689 citations
• Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables (2018) — 354 citations
• Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid (2017) — 102 citations
• secml: A Python Library for Secure and Explainable Machine Learning (2019) — 42 citations
• Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks (2018) — 477 citations
• Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection (2017) — 307 citations
• On Security and Sparsity of Linear Classifiers for Adversarial Settings (2016) — 26 citations
• Secure Kernel Machines against Evasion Attacks (2016) — 80 citations