2 papers
cs.CR2026
ClawLess: A Security Model of AI Agents
Hongyi Lu, Nian Liu, Shuai Wang +1
Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces si…
cs.CR2026
GPU-Fuzz: Finding Memory Errors in Deep Learning Frameworks
Zihao Li, Hongyi Lu, Yanan Guo +3
GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficien…