3 papers
cs.CR2025
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
Julien Piet, Xiao Huang, Dennis Jacob +7
Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulne…
cs.CR2024
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
Julien Piet, Maha Alrashed, Chawin Sitawarin +5
Large Language Models (LLMs) are attracting significant research attention due to their instruction-following abilities, allowing users and developers to leverage LLMs for a variet…
math.OC2014
Input Selection for Performance and Controllability of Structured Linear Descriptor Systems
Andrew Clark, Basel Alomair, Linda Bushnell +1
A common approach to controlling complex networks is to directly control a subset of input nodes, which then controls the remaining nodes via network interactions. While techniques…