Xuwang Yin

Researcher, Independent Researcher

Joined

July 2019

Names

Xuwang Yin

Emails

****@gmail.com (Confirmed)

****@virginia.edu (Confirmed)

****@safe.ai (Confirmed)

****@virginia.edu (Confirmed)

Personal Links

Career & Education History

Researcher

Independent Researcher (gmail.com)

2025 – 2026

Researcher

Center for AI Safety (safe.ai)

2022 – 2025

PhD student

University of Virginia (virginia.edu)

2016 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Gustavo Rohde

2018 – 2022

Coauthor

Chun Yang

2011 – 2014

Coauthor

Yan Yan

2011 – 2014

Coauthor

Yan Yan

2011 – 2014

Coauthor

Xu-cheng Yin

2011 – 2014

Expertise

Adversarial Machine Learning

Machine Learning Security

Energy-Based Models

2018 – Present

Multimodal learning with vision and language

Image captioning

2016 – 2018

Publications

Beyond Truthfulness: Evaluating Honesty in Large Language Models
Richard Ren, Arunim Agarwal, Mantas Mazeika, Cristina Menghini, Brad Kenstler, Robert Vacareanu, Mick Yang, Isabelle Barrass, Alice Gatti, Xuwang Yin, Eduardo Trevino, Matias Geralnik, Dean Lee, Summer Yue, Dan Hendrycks
- Submitted to ICLR 2026
- Readers: Everyone
Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
Xuwang Yin, Claire Zhang, Julie Steele, Nir N Shavit, Tony T. Wang
- ICLR 2026 Poster
- Readers: Everyone
Learning Globally Optimized Language Structure via Adversarial Training
Xuwang Yin
- OpenReview Archive Direct Upload
- Readers: Everyone
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
Mantas Mazeika, Xuwang Yin, Rishub Tamirisa, Jaehyuk Lim, Bruce W. Lee, Richard Ren, Long Phan, Norman Mu, Oliver Zhang, Dan Hendrycks
- NeurIPS 2025 spotlight
- Readers: Everyone
Evaluating Model Robustness Against Unforeseen Adversarial Attacks
Maximilian Kaufmann, Daniel Kang, Yi Sun, Xuwang Yin, Steven Basart, Mantas Mazeika, Adam Dziedzic, Franziska Boenisch, Tom B Brown, Abhinav Kommula, Oliver Zhang, Akul Arora, Jacob Steinhardt, Dan Hendrycks
- Submitted to ICLR 2025
- Readers: Everyone
RenderAttack: Hundreds of Adversarial Attacks Through Differentiable Texture Generation
Dron Hazra, Alex Bie, Mantas Mazeika, Xuwang Yin, Andy Zou, Dan Hendrycks, Maximilian Kaufmann
- AdvML-Frontiers 2024
- Readers: Everyone
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Richard Ren, Steven Basart, Adam Khoja, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Alexander Pan, Gabriel Mukobi, Ryan Hwang Kim, Stephen Fitz, Dan Hendrycks
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, Dan Hendrycks
- ICML 2024 Poster
- Readers: Everyone
Enhancing Neural Network Transparency through Representation Analysis
Andy Zou, Long Phan, Sarah Li Chen, James Campbell, Phillip Huang Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Annah Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Troy Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J Zico Kolter et al. (1 additional authors not shown)
- Submitted to ICLR 2024
- Readers: Everyone
Evaluating Robustness to Unforeseen Adversarial Attacks
Maximilian Kaufmann, Daniel Kang, Yi Sun, Xuwang Yin, Steven Basart, Mantas Mazeika, Adam Dziedzic, Akul Arora, Franziska Boenisch, Tom B Brown, Abhinav Kommula, Oliver Zhang, Jacob Steinhardt, Dan Hendrycks
- Submitted to ICLR 2024
- Readers: Everyone

View all 20 publications

Co-Authors

View all 76 co-authors