1 citations · 3 across the 5 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CR2024★ 1 cited
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang +3
Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerabil…
cs.CR2024★ 1 cited
Robustifying Safety-Aligned Large Language Models through Clean Data Curation
Xiaoqun Liu, Jiacheng Liang, Muchao Ye +1
Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of…