Andy Zou
13 papers · 2021–2026 · 4 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (36) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π₯
Mega-Team Β· Squad
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(67)
Venues
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(9)
Machine Learning
(6)
Deep Learning
(5)
Natural Language Processing
(5)
Learning Types Β· Deep Learning
(4)
Application Areas
(3)
Learning Types Β· Machine Learning
(3)
Resources & Methods
(3)
Computer Vision
(2)
Applications Β· Natural Language Processing
(2)
Optimization & Theory
(2)
Data Science & Analytics
(1)
Interdisciplinary
(1)
Applications Β· Data Science & Analytics
(1)
Keywords
adversarial robustness
(3)
large language model
(3)
adversarial attack
(3)
anomaly detection
(2)
language model
(2)
adversarial training
(2)
temporal reasoning
(1)
data augmentation
(1)
model security
(1)
robustness certification
(1)
evaluation framework
(1)
affective computing
(1)
model alignment
(1)
event forecasting
(1)
ai safety
(1)
deep neural network
(1)
video understanding
(1)
black-box attack
(1)
question answering
(1)
visual question answering
(1)
Papers
Omni-Attack: Adversarial Attacks on Open-Ended VQA in Black-Box Multimodal LLMs
CVPR 2026
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ICLR 2025
Tamper-Resistant Safeguards for Open-Weight LLMs
ICLR 2025
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
ICML 2024
Improving Alignment and Robustness with Circuit Breakers
NeurIPS 2024
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
ICML 2024
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark
ICML 2023
Unlocking Deterministic Robustness Certification on ImageNet
NeurIPS 2023
Forecasting Future World Events With Neural Networks
NeurIPS 2022
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
NeurIPS 2022
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
CVPR 2022
Scaling Out-of-Distribution Detection for Real-World Settings
ICML 2022
Measuring Massive Multitask Language Understanding
ICLR 2021