Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Authors: Rui Yang, Yang Hong, Yichao Xu, Zhengyu Liu, Ziyang Li, Yinzhi Cao | Published: 2026-09-01
文献データベース
The Safeguard Worked. Is the LLM System Safer?
Authors: Pingyu Wu, Weiming Zhang, Nenghai Yu | Published: 2026-09-01
SingProbe Technical Report
Authors: Sing Team | Published: 2026-08-31
ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems
Authors: Shiqian Zhao, Yangfan Zhou, Xinfeng Li, Runyi Hu, Yechao Zhang, Yi Xie, Tianwei Zhang, Luu Anh Tuan | Published: 2026-08-31
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
Authors: Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon, Chanjun Park | Published: 2026-08-31
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders
Authors: Yizhe Zeng, Chenxu Niu, Wei Zhang, Hao Huang, Yunpeng Li, Dongxu Han, Dan Du, Cheng Hong, Hequn Xian, Yuling Liu | Published: 2026-08-31
Will the User Ever Know? Covert Indirect Prompt Injection on Tool-Using LLM Agents
Authors: Yunseok Lee, Yunji Kim, Woojin Lee | Published: 2026-08-31
SIR: Self-improving Red-teaming for Compute Use Agents
Authors: Chen Xiong, Zhiyuan He, Pin-Yu Chen, Stjepan Picek, Tsung-Yi Ho | Published: 2026-08-31
Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization
Authors: Dishu Yang, Jingjing Liu, Jize Li | Published: 2026-08-31
RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
Authors: Junjie Zhang, Hui Liu, Kecheng Chen, Xianbo Mo, Changsheng Chen, Haoliang Li | Published: 2026-08-27