Milad Nasr

Artificial Intelligence · 2018–2025

A researcher in the Science corpus: 12 papers; trusts 273 researchers and is trusted by 46 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 281 citations into it; #4,769 of 35,345 by trust here, #4,298 by citations
• Safety, Robustness & Interpretability — 116 citations into it; #330 of 2,251 by trust here, #296 by citations
• Computer Vision and Pattern Recognition — 87 citations into it; #7,022 of 21,575 by trust here, #7,092 by citations
• Privacy & Security — 84 citations into it; #451 of 709 by trust here, #484 by citations
• Generative Models — 35 citations into it
• Optimization & Training — 19 citations into it
• Sociology and Political Science — 16 citations into it
• Representation & Self-Supervised Learning — 15 citations into it

Whom Milad Nasr trusts overall

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

1. Alex Krizhevsky
2. Cynthia Dwork
3. Geoffrey E. Hinton
4. Kaiming He
5. Reza Shokri
6. Diederik P. Kingma
7. Yann LeCun
8. Ilya Sutskever
9. Yoshua Bengio
10. Ilya Mironov

Who trusts Milad Nasr overall

1. Liwei Song
2. Reza Shokri
3. Nicholas Carlini
4. Stephanie L. Hyland
5. Prateek Mittal
6. Florian Tramèr
7. Li Li
8. Ahmed Salem
9. Maria Rigaki
10. Fan Mo

Papers from Milad Nasr's perspective

Ordered by how strongly the researchers Milad Nasr 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. Gradient-based learning applied to document recognition
5. Attention is All you Need (Neural Information Processing Systems)
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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Extracting Training Data from Diffusion Models (2023) — 986 citations
• Scalable Extraction of Training Data from (Production) Language Models (2023) — 592 citations
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning (2018) — 1,858 citations
• Machine Learning with Membership Privacy using Adversarial Regularization (2018) — 554 citations
• Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning (2021) — 303 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
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024) — 3,818 citations
• Are aligned neural networks adversarially aligned? (2023) — 387 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising (2020) — 47 citations
• Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks (2018) — 293 citations