Florian Tramèr
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 34 papers; trusts 2,031 researchers and is trusted by 442 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,537 citations into it; #1,625 of 36,961 by trust here, #461 by citations
- Safety, Robustness & Interpretability — 577 citations into it; #87 of 2,259 by trust here, #22 by citations
- Computer Vision and Pattern Recognition — 439 citations into it; #16,066 of 21,973 by trust here, #7,822 by citations
- Privacy & Security — 318 citations into it; #87 of 710 by trust here, #57 by citations
- Signal Processing — 174 citations into it; #3,929 of 7,592 by trust here, #825 by citations
- Computer Networks and Communications — 153 citations into it; #1,785 of 9,996 by trust here, #380 by citations
- Optimization & Training — 140 citations into it
- Information Systems — 139 citations into it
Whom Florian Tramèr trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Ian J. Goodfellow
- Nicholas Carlini
- Geoffrey E. Hinton
- Christian Szegedy
- Kaiming He
- Diederik P. Kingma
- Nicolas Papernot
- Yoshua Bengio
- Yann LeCun
Who trusts Florian Tramèr overall
- Nicholas Carlini
- Nicolas Papernot
- Tianyu Pang
- Bo Li
- Ian J. Goodfellow
- Francesco Croce
- Bernt Schiele
- Peter Kairouz
- Ahmed Salem
- Yinpeng Dong
Papers from Florian Tramèr's perspective
Ordered by how strongly the researchers Florian Tramèr 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)
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- 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
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- Extracting Training Data from Large Language Models (2020) — 3,168 citations
- Ensemble Adversarial Training: Attacks and Defenses (2017) — 3,060 citations
- Quantifying Memorization Across Neural Language Models (2022) — 944 citations
- Stealing Machine Learning Models via Prediction APIs (2016) — 2,163 citations
- Counterfactual Memorization in Neural Language Models (2021) — 203 citations
- Advances and Open Problems in Federated Learning (2019) — 9,019 citations
- The Space of Transferable Adversarial Examples (2017) — 602 citations
- Large Language Models Can Be Strong Differentially Private Learners (2021) — 533 citations
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (2018) — 492 citations
- What Does it Mean for a Language Model to Preserve Privacy? (2022) — 331 citations
- Extracting Training Data from Diffusion Models (2023) — 986 citations
- Adversarial Training and Robustness for Multiple Perturbations (2019) — 426 citations
- Scalable Extraction of Training Data from (Production) Language Models (2023) — 592 citations
- Membership Inference Attacks From First Principles (2021) — 1,168 citations
- Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy (2022) — 147 citations
- Poisoning Web-Scale Training Datasets is Practical (2023) — 362 citations
- AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning (2018) — 65 citations
- Are aligned neural networks adversarially aligned? (2023) — 387 citations
- On Adaptive Attacks to Adversarial Example Defenses (2020) — 979 citations