Dan Hendrycks
29 papers · 2018–2025 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (61) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(14)
π₯
Mega-Team Β· Squad
π§¬
Topic Evolution
π
Triple Crown
π
Keyword Champion
(2)
π§
Keyword Pioneer
π
Renaissance Researcher
(6)
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(118)
Top co-authors
Research topics
Machine Learning
(17)
Artificial Intelligence
(16)
Core AI
(16)
Deep Learning
(10)
Learning Types Β· Machine Learning
(10)
Application Areas
(8)
Learning Types Β· Deep Learning
(8)
Core Methods
(7)
Natural Language Processing
(6)
Optimization & Theory
(5)
Computer Vision
(3)
Applications
(3)
Architectures
(3)
Resources & Methods
(3)
Analysis
(2)
Keywords
out-of-distribution detection
(7)
anomaly detection
(6)
adversarial robustness
(5)
large language model
(4)
data augmentation
(3)
language model
(3)
image classification
(3)
uncertainty estimation
(3)
out-of-distribution robustness
(2)
model robustness
(2)
open category detection
(2)
adversarial attack
(2)
adversarial example
(2)
distribution shift
(2)
deep neural network
(2)
pac learning
(2)
ai safety
(2)
question answering
(2)
benchmark evaluation
(2)
label noise
(2)
Papers
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ICLR 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
ICLR 2025
Tamper-Resistant Safeguards for Open-Weight LLMs
ICLR 2025
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
ICML 2024
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
ICML 2024
Improving Alignment and Robustness with Circuit Breakers
NeurIPS 2024
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
NeurIPS 2024
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
ICML 2024
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
NeurIPS 2023
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark
ICML 2023
MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding
EMNLP 2023
A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness
ECCV 2022
Forecasting Future World Events With Neural Networks
NeurIPS 2022
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
NeurIPS 2022
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
NeurIPS 2022
PAC Guarantees and Effective Algorithms for Detecting Novel Categories
JMLR 2022
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
CVPR 2022
Scaling Out-of-Distribution Detection for Real-World Settings
ICML 2022
Aligning AI With Shared Human Values
ICLR 2021
Measuring Massive Multitask Language Understanding
ICLR 2021
Natural Adversarial Examples
CVPR 2021
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
ICCV 2021
Pretrained Transformers Improve Out-of-Distribution Robustness
ACL 2020
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
ICLR 2019
Deep Anomaly Detection with Outlier Exposure
ICLR 2019
Using Pre-Training Can Improve Model Robustness and Uncertainty
ICML 2019
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
NeurIPS 2019
Open Category Detection with PAC Guarantees
ICML 2018
Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
NeurIPS 2018