2 papers
cs.CR2026
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang +26
We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to prev…
cs.CR2025
SoK: A Beginner-Friendly Introduction to Fault Injection Attacks
Christopher Simon Liu, Fan Wang, Patrick Gould +1
Fault Injection is the study of observing how systems behave under unusual stress, environmental or otherwise. In practice, fault injection involves testing the limits of computer…