2 papers
cs.CR2026
Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
Songze Li, Ruishi He, Xiaojun Jia +2
Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, th…
cs.CR2025
ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
Jin Xie, Ruishi He, Songze Li +2
Parameter-efficient fine-tuning (PEFT) has emerged as a practical solution for adapting large language models (LLMs) to custom datasets with significantly reduced computational cos…