Matt Fredrikson
Artificial Intelligence · 2014–2024
A researcher in the Science corpus: 17 papers; trusts 709 researchers and is trusted by 281 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 328 citations into it; #1,926 of 36,961 by trust here, #1,024 by citations
- Safety, Robustness & Interpretability — 127 citations into it; #68 of 2,259 by trust here, #67 by citations
- Computer Vision and Pattern Recognition — 87 citations into it
- Privacy & Security — 51 citations into it; #178 of 710 by trust here, #67 by citations
- Sociology and Political Science — 39 citations into it
- Signal Processing — 34 citations into it
- Information Systems — 31 citations into it
- Natural Language Processing — 28 citations into it
Whom Matt Fredrikson trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Cynthia Dwork
- Diederik P. Kingma
- Yann LeCun
- Geoffrey E. Hinton
- Karen Simonyan
- Yoshua Bengio
- Ian J. Goodfellow
- Ilya Sutskever
- Christian Szegedy
Who trusts Matt Fredrikson overall
- Nicolas Papernot
- Nicholas Carlini
- Liwei Song
- Reza Shokri
- Samuel Yeom
- Milad Nasr
- Congzheng Song
- Ziqi Yang
- Florian Tramèr
- Briland Hitaj
Papers from Matt Fredrikson's perspective
Ordered by how strongly the researchers Matt Fredrikson trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
Their papers
- The Limitations of Deep Learning in Adversarial Settings (2015) — 4,317 citations
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (2015) — 3,376 citations
- Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting (2017) — 1,558 citations
- Universal and Transferable Adversarial Attacks on Aligned Language Models (2023) — 3,387 citations
- Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference (2019) — 327 citations
- The Unintended Consequences of Overfitting: Training Data Inference Attacks (2017) — 41 citations
- Representation Engineering: A Top-Down Approach to AI Transparency (2023) — 1,173 citations
- Feature-Wise Bias Amplification (2018) — 52 citations
- A Methodology for Formalizing Model-Inversion Attacks (2016) — 191 citations
- Globally-Robust Neural Networks (2021) — 156 citations
- Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models (2020) — 10 citations
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2024) — 322 citations
- Improving Alignment and Robustness with Circuit Breakers (2024) — 311 citations
- Influence-Directed Explanations for Deep Convolutional Networks (2018) — 80 citations
- Proxy Non-Discrimination in Data-Driven Systems (2017) — 59 citations
- Satisfiability modulo counting: a new approach for analyzing privacy properties (2014) — 31 citations
- Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing (2014) — 908 citations