Matthew Jagielski

Artificial Intelligence · 2018–2023

A researcher in the Science corpus: 16 papers; trusts 226 researchers and is trusted by 24 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 575 citations into it; #7,336 of 35,345 by trust here, #1,486 by citations
• Safety, Robustness & Interpretability — 265 citations into it; #625 of 2,251 by trust here, #157 by citations
• Computer Vision and Pattern Recognition — 171 citations into it
• Natural Language Processing — 135 citations into it
• Large Language Models — 107 citations into it; #368 of 799 by trust here, #188 by citations
• Evaluation & Benchmarks — 88 citations into it
• Signal Processing — 80 citations into it; #6,285 of 7,572 by trust here, #5,340 by citations
• Privacy & Security — 73 citations into it

Whom Matthew Jagielski trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Diederik P. Kingma
4. Yann LeCun
5. Yoshua Bengio
6. Nicholas Carlini
7. Kaiming He
8. Ilya Sutskever
9. Jimmy Ba
10. Ian J. Goodfellow

Who trusts Matthew Jagielski overall

1. Nicholas Carlini
2. Florian Tramèr
3. Franziska Boenisch
4. Adam Dziedzic
5. Nicolas Papernot
6. Peter Kairouz
7. Karthikeyan K
8. Stella Biderman
9. Milad Nasr
10. Maria Rigaki

Papers from Matthew Jagielski's perspective

Ordered by how strongly the researchers Matthew Jagielski 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. Attention is All you Need (Neural Information Processing Systems)
5. Gradient-based learning applied to document recognition
6. Long Short-Term Memory
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. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Extracting Training Data from Large Language Models (2020) — 3,168 citations
• PaLM 2 Technical Report (2023) — 1,524 citations
• Quantifying Memorization Across Neural Language Models (2022) — 944 citations
• Extracting Training Data from Diffusion Models (2023) — 986 citations
• Scalable Extraction of Training Data from (Production) Language Models (2023) — 592 citations
• Counterfactual Memorization in Neural Language Models (2021) — 203 citations
• Poisoning Web-Scale Training Datasets is Practical (2023) — 362 citations
• Auditing Differentially Private Machine Learning: How Private is Private SGD? (2020) — 331 citations
• Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy (2022) — 147 citations
• Are aligned neural networks adversarially aligned? (2023) — 387 citations
• Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning (2018) — 882 citations
• Measuring Forgetting of Memorized Training Examples (2022) — 150 citations
• High Accuracy and High Fidelity Extraction of Neural Networks (2019) — 476 citations
• Differentially Private Fair Learning (2018) — 174 citations
• High-Fidelity Extraction of Neural Network Models (2019) — 36 citations
• Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks (2018) — 477 citations