J
Jacob Steinhardt
Researcher at University of California, Berkeley
Publications - 116
Citations - 8821
Jacob Steinhardt is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Robustness (computer science). The author has an hindex of 28, co-authored 93 publications receiving 5444 citations. Previous affiliations of Jacob Steinhardt include Stanford University & Massachusetts Institute of Technology.
Papers
More filters
Posted Content
Concrete Problems in AI Safety
TL;DR: A list of five practical research problems related to accident risk, categorized according to whether the problem originates from having the wrong objective function, an objective function that is too expensive to evaluate frequently, or undesirable behavior during the learning process, are presented.
Proceedings Article
Certified Defenses against Adversarial Examples
TL;DR: This work proposes a method based on a semidefinite relaxation that outputs a certificate that for a given network and test input, no attack can force the error to exceed a certain value, providing an adaptive regularizer that encourages robustness against all attacks.
Posted Content
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
Dan Hendrycks,Steven Basart,Norman Mu,Saurav Kadavath,Frank Wang,Evan Dorundo,Rahul Desai,Tyler Zhu,Samyak Parajuli,Mike Guo,Dawn Song,Jacob Steinhardt,Justin Gilmer +12 more
TL;DR: It is found that using larger models and artificial data augmentations can improve robustness on real-world distribution shifts, contrary to claims in prior work.
Posted Content
Natural Adversarial Examples
TL;DR: This work introduces two challenging datasets that reliably cause machine learning model performance to substantially degrade and curates an adversarial out-of-distribution detection dataset called IMAGENET-O, which is the first out- of-dist distribution detection dataset created for ImageNet models.
Posted ContentDOI
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Miles Brundage,Shahar Avin,Jack Clark,Helen Toner,Peter Eckersley,Ben Garfinkel,Allan Dafoe,Paul Scharre,Thomas Zeitzoff,Bobby Filar,Hyrum S. Anderson,Heather M. Roff,Gregory C. Allen,Jacob Steinhardt,Carrick Flynn,Seán Ó hÉigeartaigh,Simon Beard,Haydn Belfield,Sebastian Farquhar,Clare Lyle,Rebecca Crootof,Owain Evans,Michael Page,Joanna J. Bryson,Roman V. Yampolskiy,Dario Amodei +25 more
TL;DR: The following organisations are named on the report: Future of Humanity Institute, University of Oxford, Centre for the Study of Existential Risk, Universityof Cambridge, Center for a New American Security, Electronic Frontier Foundation, OpenAI.