Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Alwin Peng
Observed name:
Peng, Alwin
Observed institution:
Anthropic (United States)
OpenAlex ID:
A5114654373
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
2025
·
Sharma, Mrinank
, Tong, Meg
, et al.
·
arXiv (Cornell University)
·
7
PDF
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
2026
·
Sel, Bilgehan
, He, Xuanli
, et al.
·
arXiv (Cornell University)
PDF
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
2026
·
Cunningham, Hoagy
, Wei, Jerry
, et al.
·
arXiv (Cornell University)
PDF
Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
2024
·
Peng, Alwin
, Michael, Julian
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
4
Citation count:
7
H-index:
1
I10-index:
Year
Topic
Type
