Ahmed Salem

Artificial Intelligence · 2018–2024

A researcher in the Science corpus: 8 papers; trusts 108 researchers and is trusted by 21 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 281 citations into it; #8,069 of 35,345 by trust here, #6,103 by citations
• Safety, Robustness & Interpretability — 166 citations into it
• Privacy & Security — 58 citations into it
• Computer Vision and Pattern Recognition — 51 citations into it; #15,701 of 21,575 by trust here, #13,815 by citations
• Signal Processing — 42 citations into it
• Natural Language Processing — 32 citations into it
• Safety Research — 18 citations into it; #5,522 of 5,829 by trust here, #3,224 by citations
• Sociology and Political Science — 17 citations into it

Whom Ahmed Salem trusts overall

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

1. Reza Shokri
2. Geoffrey E. Hinton
3. Ian J. Goodfellow
4. Alex Krizhevsky
5. Yoshua Bengio
6. Karen Simonyan
7. Yann LeCun
8. Congzheng Song
9. Diederik P. Kingma
10. Ilya Sutskever

Who trusts Ahmed Salem overall

1. Liwei Song
2. Maria Rigaki
3. Nicholas Carlini
4. Lixu Wang
5. Yang Zhang
6. Zheng Li
7. Prateek Mittal
8. Christopher A. Choquette-Choo
9. Bargav Jayaraman
10. Florian Tramèr

Papers from Ahmed Salem's perspective

Ordered by how strongly the researchers Ahmed Salem 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. Long Short-Term Memory
5. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
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

• ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018) — 1,184 citations
• MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples (2019) — 475 citations
• Dynamic Backdoor Attacks Against Machine Learning Models (2020) — 335 citations
• Analyzing Leakage of Personally Identifiable Information in Language Models (2023) — 411 citations
• Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack (2024) — 370 citations
• BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements (2020) — 363 citations
• Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning (2019) — 298 citations
• MLCapsule: Guarded Offline Deployment of Machine Learning as a Service (2018) — 124 citations