FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
Authors: Fanxiao Li, Jiaying Wu, Tingchao Fu, Natasha Jaques, Wei Zhou, Min-Yen Kan | Published: 2026-05-12
CTFusion: A CTF-based Benchmark for LLM Agent Evaluation
Authors: Dongjun Lee, Ga-eun Bae, Insu Yun | Published: 2026-05-12
Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
Authors: Zi Liang, Ronghua Li, Yanyun Wang, Qingqing Ye, Haibo Hu | Published: 2026-05-12
Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights
Authors: Saba Pourhanifeh, AbdulAziz AbdulGhaffar, Ashraf Matrawy | Published: 2026-05-11
LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges
Authors: Johann Knechtel, Ozgur Sinanoglu, Ramesh Karri | Published: 2026-05-11
Re-Triggering Safeguards within LLMs for Jailbreak Detection
Authors: Zheng Lin, Zhenxing Niu, Haoxuan Ji, Yuzhe Huang, Haichang Gao | Published: 2026-05-11
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
Authors: Zheng Lin, Zhenxing Niu, Haoxuan Ji, Haichang Gao | Published: 2026-05-11
When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications
Authors: Farzad Nourmohammadzadeh Motlagh, Mehrdad Hajizadeh, Mehryar Majd, Pejman Najafi, Feng Cheng, Christoph Meinel | Published: 2026-05-11
Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
Authors: Qinghua Mao, Xi Lin, Jinze Gu, Jun Wu, Siyuan Li, Yuliang Chen | Published: 2026-05-11
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
Authors: Yue Li, Xiao Li, Hao Wu, Yue Zhang, Yechao Zhang, Yating Liu, Fengyuan Xu, Sheng Zhong | Published: 2026-05-11