Andy Zou
Scholar

Andy Zou

Google Scholar ID: zir09KwAAAAJ
PhD Student, Carnegie Mellon University
ML SafetyAI Safety
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
14,753
 
H-index
19
 
i10-index
21
 
Publications
20
 
Co-authors
3
list available
Contact
No contact links provided.
Publications
14 items
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
2026
Cited
0
Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
2025
Cited
0
A Definition of AGI
2025
Cited
0
D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
2025
Cited
0
Evaluating Language Model Reasoning about Confidential Information
2025
Cited
0
TextQuests: How Good are LLMs at Text-Based Video Games?
2025
Cited
0
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
2025
Cited
0
Adversarial Attacks on Robotic Vision Language Action Models
2025
Cited
0
Resume (English only)
Co-authors
3 total
Dan Hendrycks
Dan Hendrycks
Director of the Center for AI Safety (advisor for xAI and Scale)
Matt Fredrikson
Matt Fredrikson
Carnegie Mellon University
Zico Kolter
Zico Kolter
Carnegie Mellon University