Dylan Hadfield-Menell
3 papers in the PaperMetrix corpus
Papers by this author
-
On the Geometry of Adversarial Examples
2018 · arXiv (Cornell University)
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the …
-
Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
2023 · ACM Transactions on Recommender Systems
Recommender systems are the algorithms which select, filter, and personalize content across many of the world's largest platforms and apps. As such, their positive and negative effects on individuals and on societies have been extensively …
-
Black-Box Access is Insufficient for Rigorous AI Audits
2024
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to auditors. Recent audits of state-of-the-art AI …