Luyao Niu
University of Washington researcher; works on adversarial ML, trustworthy LLMs, and security evaluation.
- Role
- researcher
- Currently at
- University of Washington
- Unknown
- GitHub
- Unknown
- Scholar
- scholar.google.com/citations
- Papers
- 7
Cite
Notes
Only stored in your browser.
Authored papers
7Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?
arXiv 2026
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
arXiv 2025
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
preprint
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
arXiv 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
arXiv 2024
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
arXiv 2024
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
arXiv 2024
Affiliations
Frequent co-authors
10from 7 papers
Fengqing Jiang
grad-student
Radha Poovendran
professor
Zhangchen Xu
grad-student
Bhaskar Ramasubramanian
Bill Yuchen Lin
researcher
Yuetai Li
Basel Alomair
Bo Li
Chunjiang Liu
Dinuka Sahabandu