Jailbreaking via Activation Dilution: Neuron-Guided Adaptive Decomposition of Language Models
Jiahang Wang, Chenglong Fu, Xiaojiang Du, Bo Luo
Ask Lune
Ask anything. The answer shows its sources.
Lune reads the papers around it, then shows you the passages behind every answer.
Related papers
- Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language ModelsHaojie Hao, Jiakai Wang, Aishan Liu, Yuqing Ma et al.AAAI 2026
- Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language ModelsLang Gao, Jiahui Geng, Xiangliang Zhang, Preslav Nakov et al.ACL 2025
- From "Sure" to "Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeuronsYuyou Gan, Qingming Li, Junhao Li, Zhi Chen et al.ICLR 2026
- Activation-Guided Local Editing for Jailbreaking AttacksJiecong Wang, Haoran Li, Hao Peng, Ziqian Zeng et al.ACL 2026 · 1 citation
- Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained OptimizationKai Hu, Weichen Yu, Yining Li, Tianjun Yao et al.NeurIPS 2024 · 31 citations
