ResearchTrend.AI
Probing the Robustness of Large Language Models Safety to Latent Perturbations

Probing the Robustness of Large Language Models Safety to Latent Perturbations

Tianle Gu
Kexin Huang
Zongqi Wang
Yixu Wang
Jie Li
Yuanqi Yao
Yang Yao
Yujiu Yang
Yan Teng
Yingchun Wang
ArXiv (abs)PDFHTML

Papers citing "Probing the Robustness of Large Language Models Safety to Latent Perturbations"

1 / 1 papers shown
Title
The Rogue Scalpel: Activation Steering Compromises LLM Safety
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Anton Korznikov
Andrey V. Galichin
Alexey Dontsov
Oleg Y. Rogov
Ivan Oseledets
Elena Tutubalina
LLMSVAAML
12
0
0
26 Sep 2025