Haydn Belfield

Political Science and International Relations · 2018–2021

A researcher in the Science corpus: 4 papers; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Political Science and International Relations — 8 citations into it

Whom Haydn Belfield trusts overall

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

1. Steffen Ganghof
2. Sara Hajian
3. M. Verbruggen
4. E. Adler

Papers from Haydn Belfield's perspective

Ordered by how strongly the researchers Haydn Belfield trusts endorse each paper. Same corpus, a different order for every researcher.

1. Intriguing properties of neural networks
2. Explaining and Harnessing Adversarial Examples
3. Towards Deep Learning Models Resistant to Adversarial Attacks
4. Axiomatic Attribution for Deep Networks
5. Model Cards for Model Reporting
6. Concrete Problems in AI Safety
7. The mythos of model interpretability
8. Calibrating Noise to Sensitivity in Private Data Analysis
9. Datasheets for datasets
10. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

Their papers

• The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation (2018) — 923 citations
• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020) — 480 citations
• Filling gaps in trustworthy development of AI (2021) — 63 citations
• Activism by the AI Community: Analysing Recent Achievements and Future Prospects (2020) — 51 citations