Nicholas Carlini
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 54 papers; trusts 2,939 researchers and is trusted by 4,841 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,671 citations into it; #324 of 36,961 by trust here, #248 by citations
- Safety, Robustness & Interpretability — 782 citations into it; #4 of 2,259 by trust here, #6 by citations
- Computer Vision and Pattern Recognition — 668 citations into it; #965 of 21,973 by trust here, #928 by citations
- Signal Processing — 260 citations into it; #173 of 7,592 by trust here, #174 by citations
- Natural Language Processing — 189 citations into it; #5,431 of 5,725 by trust here, #1,885 by citations
- Representation & Self-Supervised Learning — 166 citations into it; #794 of 3,156 by trust here, #483 by citations
- Optimization & Training — 160 citations into it
- Evaluation & Benchmarks — 128 citations into it
Whom Nicholas Carlini trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Christian Szegedy
- Geoffrey E. Hinton
- Ian J. Goodfellow
- Diederik P. Kingma
- Yoshua Bengio
- Kaiming He
- Ilya Sutskever
- Yann LeCun
- Alex Graves
Who trusts Nicholas Carlini overall
- Florian Tramèr
- Anish Athalye
- Tianyu Pang
- Logan Engstrom
- Matthias Hein
- Andrew Ilyas
- Nicolas Papernot
- Dan Hendrycks
- Huan Zhang
- Bo Li
Papers from Nicholas Carlini's perspective
Ordered by how strongly the researchers Nicholas Carlini 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Extracting Training Data from Large Language Models (2020) — 3,168 citations
- Towards Evaluating the Robustness of Neural Networks (2016) — 10,045 citations
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples (2018) — 3,560 citations
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020) — 4,872 citations
- MixMatch: A Holistic Approach to Semi-Supervised Learning (2019) — 3,592 citations
- Deduplicating Training Data Makes Language Models Better (2021) — 926 citations
- The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks (2018) — 1,449 citations
- Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods (2017) — 1,995 citations
- Quantifying Memorization Across Neural Language Models (2022) — 944 citations
- Measuring Robustness to Natural Distribution Shifts in Image Classification (2020) — 698 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring (2019) — 796 citations
- Unsolved Problems in ML Safety (2021) — 390 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring (2020) — 479 citations
- Adversarial Examples Are a Natural Consequence of Test Error in Noise (2019) — 343 citations
- Counterfactual Memorization in Neural Language Models (2021) — 203 citations
- The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets (2018) — 200 citations
- Defensive Distillation is Not Robust to Adversarial Examples (2016) — 353 citations
- Audio Adversarial Examples: Targeted Attacks on Speech-to-Text (2018) — 1,193 citations
- Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong (2017) — 246 citations
- On Evaluating Adversarial Robustness (2019) — 1,007 citations