2 papers
cs.CL2025
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…
cs.LG2025
Kryptonite-N: Machine Learning Strikes Back
Albus Li, Nathan Bailey, Will Sumerfield +1
Quinn et al propose challenge datasets in their work called ``Kryptonite-N". These datasets aim to counter the universal function approximation argument of machine learning, breaki…