Andy Zou

PhD student, CMU, Carnegie Mellon University

Joined

September 2020

Names

Andy Zou (Preferred)

Emails

****@berkeley.edu (Confirmed)

****@cmu.edu (Confirmed)

****@cs.cmu.edu (Confirmed)

Personal Links

DBLP

Career & Education History

PhD student

CMU, Carnegie Mellon University (andrew.cmu.edu)

2022 – Present

MS student

University of California Berkeley (berkeley.edu)

2021 – 2022

Undergrad student

University of California Berkeley (berkeley.edu)

2018 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Zico Kolter

2022 – 2027

PhD Advisor

Matt Fredrikson

2022 – 2027

Expertise

ml safety

ai safety

alignment

robustness

monitoring

transparency

2020 – Present

Publications

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
Justin W Lin, Eliot Krzysztof Jones, Donovan Julian Jasper, Ethan Jun-shen Ho, Anna Wu, Arnold Tianyi Yang, Neil Perry, Andy Zou, Matt Fredrikson, J Zico Kolter, Percy Liang, Dan Boneh, Daniel E. Ho
- ICLR 2026 Poster
- Readers: Everyone
TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models
Yue Huang, Chujie Gao, Siyuan Wu, Haoran Wang, Xiangqi Wang, Jiayi Ye, Yujun Zhou, Yanbo Wang, Jiawen Shi, Qihui Zhang, Han Bao, Zhaoyi Liu, Yuan Li, Tianrui Guan, Peiran Wang, Haomin Zhuang, Dongping Chen, Kehan Guo, Andy Zou, Bryan Hooi et al. (44 additional authors not shown)
- ICLR 2026 Poster
- Readers: Everyone
Adversarial Attacks on Robotic Vision Language Action Models
Eliot Krzysztof Jones, Alexander Robey, Andy Zou, Zachary Ravichandran, George J. Pappas, Hamed Hassani, Matt Fredrikson, J Zico Kolter
- RSS 2025 Workshop ReliableRobotics
- Readers: Everyone
Transferable Visual Adversarial Attacks for Proprietary Multimodal Large Language Models
Kai Hu, Weichen Yu, Alexander Robey, Li Zhang, Andy Zou, Haoqi Hu, Chengming Xu, Matt Fredrikson
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
Andy Zou, Maxwell Lin, Eliot Krzysztof Jones, Micha V. Nowak, Mateusz Dziemian, Nick Winter, Valent Nathanael, Ayla Croft, Xander Davies, Jai Patel, Robert Kirk, Yarin Gal, Dan Hendrycks, J Zico Kolter, Matt Fredrikson
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Safety Pretraining: Toward the Next Generation of Safe AI
Pratyush Maini, Sachin Goyal, Dylan Sam, Alexander Robey, Yash Savani, Yiding Jiang, Andy Zou, Matt Fredrikson, Zachary Chase Lipton, J Zico Kolter
- NeurIPS 2025 poster
- Readers: Everyone
Which Network is Trojaned? Increasing Trojan Evasiveness for Model-Level Detectors
Mantas Mazeika, Andy Zou, Akul Arora, Pavel Pleskov, Dawn Song, Bo Li, David Forsyth
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Tamper-Resistant Safeguards for Open-Weight LLMs
Rishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti, Tarun Suresh, Maxwell Lin, Justin Wang, Rowan Wang, Ron Arel, Andy Zou, Dawn Song, Bo Li, Dan Hendrycks, Mantas Mazeika
- ICLR 2025 Poster
- Readers: Everyone
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, J Zico Kolter, Matt Fredrikson, Yarin Gal, Xander Davies
- ICLR 2025 Poster
- Readers: Everyone
Transferable Adversarial Attack on Vision-enabled Large Language Models
Kai Hu, Weichen Yu, Alexander Robey, Andy Zou, Chengming Xu, Haoqi Hu, Matt Fredrikson
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 37 publications

Co-Authors

View all 638 co-authors