Detecting Malicious Agent Skills in the Wild using Attention
Authors: Bacem Etteib, Daniele Lunghi, Tégawendé F. Bissyandé | Published: 2026-06-22
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
Authors: Yinpeng Wu, Yitong Chen, Lixiang Wang, Jinyu Gu, Zhichao Hua, Yubin Xia | Published: 2026-06-22
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
Authors: Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan, Chee Seng Chan, Kok-Seng Wong | Published: 2026-06-22
GIF: Locally Sound Geometric Information Flow Control for LLMs
Authors: Adam Storek, Nikolaus Holzer, Zhuo Zhang, Suman Jana | Published: 2026-06-22
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Authors: Advik Raj Basani, Anshuman Chhabra | Published: 2026-06-22
Understanding the (In)Security of Vibe-Coded Applications
Authors: Junquan Deng, Zhiyu Fan, Ruijie Meng | Published: 2026-06-22
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Authors: Ruixiao Lin, Xinhao Deng, Qingming Li, Jianan Ma, Yunhao Feng, Yuqi Qing, Zhenyuan Li, Yechao Zhang, Shiwen Cui, Changhua Meng, Tianwei Zhang, Xingjun Ma, Qi Li, Ke Xu, Shouling Ji | Published: 2026-06-22
VCT: A Verifiable Transcript System for LLM Conversations
Authors: Ruilin Xing, Feihong Li, Jiayue Liu, Jiali Zheng, Wei Liu, Wanzhi Xie | Published: 2026-06-22
Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models
Authors: Linghan Chen, Kaiyan Ji, Minyu Guo | Published: 2026-06-22
The Unseen Hand: Manipulating Model Fairness and SHAP with Targeted Identity Re-Association Attacks
Authors: Sannaan Khan, Muhammad U. S. Khan | Published: 2026-06-22