Luca Melis

Artificial Intelligence · 2015–2018

A researcher in the Science corpus: 6 papers; trusts 227 researchers and is trusted by 44 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 201 citations into it; #5,489 of 35,345 by trust here, #3,859 by citations
• Safety, Robustness & Interpretability — 79 citations into it; #1,318 of 2,251 by trust here, #1,404 by citations
• Computer Vision and Pattern Recognition — 70 citations into it; #7,204 of 21,575 by trust here, #5,890 by citations
• Privacy & Security — 68 citations into it; #182 of 709 by trust here, #74 by citations
• Generative Models — 35 citations into it; #1,467 of 1,956 by trust here, #1,021 by citations
• Sociology and Political Science — 24 citations into it
• Computer Networks and Communications — 22 citations into it
• Information Systems — 22 citations into it

Whom Luca Melis trusts overall

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

1. Geoffrey E. Hinton
2. Cynthia Dwork
3. Diederik P. Kingma
4. Alex Krizhevsky
5. Yoshua Bengio
6. Yann LeCun
7. Reza Shokri
8. Ilya Sutskever
9. Ian J. Goodfellow
10. Individualized Treat

Who trusts Luca Melis overall

1. Congzheng Song
2. Lingjuan Lyu
3. Milad Nasr
4. Rasmus Pagh
5. Ahmed Salem
6. Henry Corrigan-Gibbs
7. Hong Chang
8. Reza Shokri
9. Vitaly Shmatikov
10. Yang Zhang

Papers from Luca Melis's perspective

Ordered by how strongly the researchers Luca Melis 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. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• LOGAN: Evaluating Privacy Leakage of Generative Models Using Generative Adversarial Networks (2017) — 107 citations
• LOGAN: Membership Inference Attacks Against Generative Models (2017) — 600 citations
• Differentially Private Mixture of Generative Neural Networks (2017) — 138 citations
• Exploiting Unintended Feature Leakage in Collaborative Learning (2018) — 1,798 citations
• Efficient Private Statistics with Succinct Sketches (2015) — 129 citations
• Inference Attacks Against Collaborative Learning (2018) — 110 citations