Picture for Arvind Narayanan

Arvind Narayanan

AI Risk Management Should Incorporate Both Safety and Security

Add code
May 29, 2024
Viaarxiv icon

A Safe Harbor for AI Evaluation and Red Teaming

Add code
Mar 07, 2024
Figure 1 for A Safe Harbor for AI Evaluation and Red Teaming
Figure 2 for A Safe Harbor for AI Evaluation and Red Teaming
Figure 3 for A Safe Harbor for AI Evaluation and Red Teaming
Figure 4 for A Safe Harbor for AI Evaluation and Red Teaming
Viaarxiv icon

On the Societal Impact of Open Foundation Models

Add code
Feb 27, 2024
Figure 1 for On the Societal Impact of Open Foundation Models
Figure 2 for On the Societal Impact of Open Foundation Models
Viaarxiv icon

Foundation Model Transparency Reports

Add code
Feb 26, 2024
Viaarxiv icon

REFORMS: Reporting Standards for Machine Learning Based Science

Aug 15, 2023
Figure 1 for REFORMS: Reporting Standards for Machine Learning Based Science
Figure 2 for REFORMS: Reporting Standards for Machine Learning Based Science
Viaarxiv icon

Leakage and the Reproducibility Crisis in ML-based Science

Jul 14, 2022
Figure 1 for Leakage and the Reproducibility Crisis in ML-based Science
Figure 2 for Leakage and the Reproducibility Crisis in ML-based Science
Figure 3 for Leakage and the Reproducibility Crisis in ML-based Science
Viaarxiv icon

The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning

Apr 06, 2022
Figure 1 for The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning
Viaarxiv icon

Mitigating dataset harms requires stewardship: Lessons from 1000 papers

Add code
Aug 06, 2021
Figure 1 for Mitigating dataset harms requires stewardship: Lessons from 1000 papers
Figure 2 for Mitigating dataset harms requires stewardship: Lessons from 1000 papers
Figure 3 for Mitigating dataset harms requires stewardship: Lessons from 1000 papers
Figure 4 for Mitigating dataset harms requires stewardship: Lessons from 1000 papers
Viaarxiv icon

T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems

Add code
Jul 28, 2021
Figure 1 for T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
Figure 2 for T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
Figure 3 for T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
Figure 4 for T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
Viaarxiv icon

ViBE: A Tool for Measuring and Mitigating Bias in Image Datasets

Add code
Apr 16, 2020
Figure 1 for ViBE: A Tool for Measuring and Mitigating Bias in Image Datasets
Figure 2 for ViBE: A Tool for Measuring and Mitigating Bias in Image Datasets
Figure 3 for ViBE: A Tool for Measuring and Mitigating Bias in Image Datasets
Figure 4 for ViBE: A Tool for Measuring and Mitigating Bias in Image Datasets
Viaarxiv icon