most citedConstitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

7 citations · 7 across the 2 of their papers we have counts for

collaborators
Showing cs.PLShow all

1 paper · 1 filter

cs.PL2022

Probabilistic Total Store Ordering

Parosh Aziz Abdulla, Mohamed Faouzi Atig, Raj Aryan Agarwal +2

We present -- a probabilistic extension of the classical TSO semantics. For a given (finite-state) program, the operational sem…