Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents
Authors: Wenxin Wu, Lingyong Yan, Lei Sha, Shuaiqiang Wang, Jiashu Zhao | Published: 2026-09-30
プロンプトリーキング
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
Authors: Jiaqing Li, Shide Zhou, Zhibo Zhang, Yuxi Li, Tianlong Yu, Kailong Wang | Published: 2026-09-30
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
Authors: Fahao Chen, Linkang Du, Jinhao Zhou, Peng Li, Zhou Su | Published: 2026-09-30
ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents
Authors: Yanjie Li, Xiangyu He, Xuelong Dai, Bin Xiao | Published: 2026-09-29
Practical Secrets Extraction against Black-box LLMs
Authors: Shiqian Zhao, Siwei Jiang, Xinfeng Li, Runyi Hu, Yandan Zheng, Congyu Guo, Tianwei Zhang, Anh Tuan Luu | Published: 2026-09-29
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
Authors: Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu, Ali Zain Kaimkhani, Minghong Fang | Published: 2026-09-29
LLMs Learn to Evade Latent Monitors from Prior Feedback Alone
Authors: Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani | Published: 2026-09-29
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
Authors: Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev, Aleksandr Nikolich | Published: 2026-09-28
ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments
Authors: Daiki Chiba, Hiroki Nakano, Takashi Koide | Published: 2026-09-24
Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis
Authors: Jiling Zhou, Aisvarya Adeseye, Antti Hakkala, Seppo Virtanen, Jouni Isoaho | Published: 2026-09-21