← Search

Yuna Park

2 accepted papers

2025

M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs

ACL 2025long

We introduce a novel framework for consolidating multi-turn adversarial “jailbreak” prompts into single-turn queries, significantly reducing the manual overhead required for adversarial testing of large language models (LLMs). While multi-turn human jailbreaks have been shown to yield high attack su…

2024

REPrune: Channel Pruning via Kernel Representative Selection

AAAI 2024technical

Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning granularity, specifically at the unit of a convolution filter…

Cited by 2SourcePDFScholar