一作ICML 2026Spotlight· Social Aspects / Safety
Jailbreak to Protect: Buffering Harmful Fine-Tuning via Temporary Jailbreaking LoRA in Large Language Models
Seokil Ham · Jaehyuk Jang · Wonjun Lee · Changick Kim
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Seokil Ham · Jaehyuk Jang · Wonjun Lee · Changick Kim
Yubin Choi · Yujin Yang · Subin Kim · Seokil Ham · Seungju Cho · Jungmin Son · Youngjun Kwak · Changick Kim
Financial Large Language Models (LLMs) exhibit strong domain expertise but remain vulnerable to financially harmful prompts. To systematically assess this vulnerability, we introduce FinHarmBench , a benchmark designed to evaluate financially harmful and confusable benign prompts. Our analysis re...