Jiacheng Liang

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks

2024 · arXiv (Cornell University)

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can compromise the robustness of LLMs …