Ú. Erlingsson
Artificial Intelligence · 1996–2020
A researcher in the Science corpus: 21 papers; trusts 513 researchers and is trusted by 288 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 501 citations into it; #1,764 of 36,961 by trust here, #865 by citations
- Privacy & Security — 186 citations into it; #17 of 710 by trust here, #14 by citations
- Safety, Robustness & Interpretability — 115 citations into it; #67 of 2,259 by trust here, #45 by citations
- Information Systems — 97 citations into it; #4,717 of 9,233 by trust here, #802 by citations
- Computer Networks and Communications — 79 citations into it; #4,760 of 9,996 by trust here, #3,410 by citations
- Computer Vision and Pattern Recognition — 76 citations into it
- Sociology and Political Science — 66 citations into it; #10,771 of 22,891 by trust here, #1,854 by citations
- Natural Language Processing — 58 citations into it
Whom Ú. Erlingsson trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Cynthia Dwork
- Frank McSherry
- Alex Krizhevsky
- Geoffrey E. Hinton
- Martín Abadi
- Kobbi Nissim
- Ilya Mironov
- Yoshua Bengio
- Raef Bassily
- Adam D. Smith
Who trusts Ú. Erlingsson overall
- Badih Ghazi
- Tianhao Wang
- Jayadev Acharya
- Peter Kairouz
- Vitaly Feldman
- Borja Balle
- Rasmus Pagh
- Ravi Kumar
- Albert Cheu
- Matthew Joseph
Papers from Ú. Erlingsson's perspective
Ordered by how strongly the researchers Ú. Erlingsson trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Extracting Training Data from Large Language Models (2020) — 3,168 citations
- The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks (2018) — 1,449 citations
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data (2016) — 1,156 citations
- The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets (2018) — 200 citations
- Scalable Private Learning with PATE (2018) — 725 citations
- RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response (2014) — 2,273 citations
- Prochlo: Strong Privacy for Analytics in the Crowd (2017) — 293 citations
- Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications (2019) — 74 citations
- On the Protection of Private Information in Machine Learning Systems: Two Recent Approches (2017) — 50 citations
- Tempered Sigmoid Activations for Deep Learning with Differential Privacy (2020) — 220 citations
- Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity (2018) — 512 citations
- Making the Shoe Fit: Architectures, Initializations, and Tuning for Learning with Privacy (2019) — 65 citations
- Building a RAPPOR with the Unknown: Privacy-Preserving Learning of Associations and Data Dictionaries (2015) — 318 citations
- Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation (2020) — 94 citations
- Prototypical Examples in Deep Learning: Metrics, Characteristics, and Utility (2018) — 25 citations
- PROCHLO: Strong Privacy for Analytics in the Crowd (2017)
- Enforcing Forward-Edge Control-Flow Integrity in GCC & LLVM (2014) — 455 citations
- Control-flow integrity principles, implementations, and applications (2009) — 955 citations
- Control-flow integrity (2005) — 639 citations
- IRM enforcement of Java stack inspection (2000) — 362 citations