Dan Hendrycks

13.6k citations
22 papers · 2.3k · 3 hit papers · h-index 13

Impact in

    • Domain Adaptation and Few-Shot Learning
    • Adversarial Robustness in Machine Learning
    • Topic Modeling
    • Machine Learning and Data Classification
    • Natural Language Processing Techniques
    • Advanced Neural Network Applications
    • Multimodal Machine Learning Applications

Papers in

    • Adversarial Robustness in Machine Learning 11
    • Topic Modeling 4
    • Domain Adaptation and Few-Shot Learning 2
    • Privacy-Preserving Technologies in Data 1
    • Ethics and Social Impacts of AI 3

Dan Hendrycks

21 papers receiving 2.2k citations

Dan Hendrycks's Hit Papers

AI deception: A survey of examples, risks, and potential solutions 2024 · 112 citations
1120+1+3Years since publication200400600

Peers

Dan Hendrycks
Comparison fields: 5 of 88
  • Artificial Intelligence 1.6k
  • Computer Vision and Pattern Recognition 763
  • Health Informatics 31
  • Safety Research 125
  • Software 23
Replace Eric Wallace with:
Eric Wallace United States
Stella Biderman United States
Zhifang Sui China
Rico Sennrich Switzerland
Rich Zemel Canada
Timo Schick Germany
Minsuk Kahng United States
Edward Raff United States
Wei-Lin Chiang Taiwan
Zhuosheng Zhang China
Dan Hendrycks relative to Eric Wallace United States Eric Wallace's profile →
Citations per field
00.5×2×2.7×
Eric Wallace · 1×
Citations per year

Countries citing papers authored by Dan Hendrycks

Since Specialization
Citations

This map shows the geographic impact of Dan Hendrycks's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Dan Hendrycks with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Dan Hendrycks more than expected).

Fields of papers citing papers by Dan Hendrycks

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Dan Hendrycks. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Dan Hendrycks. The network helps show where Dan Hendrycks may publish in the future.

Co-authors

The 25 scholars most cited alongside Dan Hendrycks, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Dan Hendrycks Line = papers co-authored together Dan Hendrycks links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 22 papers — load more, or switch the sort, to bring in the rest.

#Work
1
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
Hit paper breakdown →
2021739
2
Natural Adversarial Examples
Hit paper breakdown →
2021599
3
Measuring Massive Multitask Language Understanding
2021202
4 2020198
5
AI deception: A survey of examples, risks, and potential solutions
Hit paper breakdown →
2024112
6
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
2019107
7
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
202081
8 202268
9 202437
10 202335
11 202421
12 201916
13
Visible Progress on Adversarial Images and a New Saliency Map.
201613
14 20269
15 20197
16 20237
17 20226
18 20236
19 20244
20
A Quantitative Measure of Generative Adversarial Network Distributions
20173

About Dan Hendrycks

Dan Hendrycks is a scholar working on Artificial Intelligence, Safety Research, Computer Vision and Pattern Recognition, Computer Networks and Communications and Political Science and International Relations, having authored 22 papers that have together received 2.3k indexed citations. Recurring topics across this work include Adversarial Robustness in Machine Learning (11 papers), Topic Modeling (4 papers), Ethics and Social Impacts of AI (3 papers), Domain Adaptation and Few-Shot Learning (2 papers), Privacy-Preserving Technologies in Data (1 paper), Artificial Intelligence in Law (1 paper), Software System Performance and Reliability (1 paper) and Multimodal Machine Learning Applications (1 paper). The work is most often cited by research in Artificial Intelligence (1.6k citations), Computer Vision and Pattern Recognition (763 citations), Health Informatics (31 citations), Safety Research (125 citations) and Software (23 citations). Dan Hendrycks has collaborated with scholars based in United States, China and Switzerland. Frequent co-authors include Dawn Xiaodong Song, Jacob Steinhardt, Steven Basart, Kevin Zhao, Saurav Kadavath, Justin Gilmer, Norman Mu, Mantas Mazeika, Samyak Parajuli and Tyler Zhu. Their work appears in journals such as Proceedings of the VLDB Endowment, Patterns, Nature, Lecture notes in computer science and International Conference on Learning Representations.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact