Jailbreaking via Activation Dilution: Neuron-Guided Adaptive Decomposition of Language Models
Jiahang Wang, Chenglong Fu, Xiaojiang Du, Bo Luo
问 Lune
尽管问，回答都注明出处。
Lune 会读相关的 Paper，每个回答都附上所依据的原文段落。
相关 Paper
- Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language ModelsHaojie Hao, Jiakai Wang, Aishan Liu, Yuqing Ma 等AAAI 2026
- Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language ModelsLang Gao, Jiahui Geng, Xiangliang Zhang, Preslav Nakov 等ACL 2025
- From "Sure" to "Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeuronsYuyou Gan, Qingming Li, Junhao Li, Zhi Chen 等ICLR 2026
- Activation-Guided Local Editing for Jailbreaking AttacksJiecong Wang, Haoran Li, Hao Peng, Ziqian Zeng 等ACL 2026 · 1 次引用
- Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained OptimizationKai Hu, Weichen Yu, Yining Li, Tianjun Yao 等NeurIPS 2024 · 31 次引用
