Ross Anderson

Artificial Intelligence · with Papernot · 2020–2024

A researcher in the Science corpus: 4 papers; trusts 25 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 73 citations into it
• Computer Vision and Pattern Recognition — 33 citations into it
• Safety, Robustness & Interpretability — 32 citations into it
• Natural Language Processing — 18 citations into it
• Representation & Self-Supervised Learning — 8 citations into it

Whom Ross Anderson trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Yann LeCun
4. Yoshua Bengio
5. Ilya Sutskever
6. Kaiming He
7. Christian Szegedy

Papers from Ross Anderson's perspective

Ordered by how strongly the researchers Ross Anderson 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. Attention is All you Need (Neural Information Processing Systems)
4. Gradient-based learning applied to document recognition
5. Learning Multiple Layers of Features from Tiny Images
6. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
7. Long Short-Term Memory
8. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
9. ImageNet: A large-scale hierarchical image database
10. Distributed Representations of Words and Phrases and their Compositionality (Neural Information Processing Systems)

Their papers

• The Curse of Recursion: Training on Generated Data Makes Models Forget (2023) — 507 citations
• Sponge Examples: Energy-Latency Attacks on Neural Networks (2020) — 192 citations
• AI models collapse when trained on recursively generated data (2024) — 891 citations
• Manipulating SGD with Data Ordering Attacks (2021) — 122 citations