5 papers
: Improving Agent Safety through Multi-Stage Defense
Zibo Xiao, Haoyu Wang, Jun Sun
Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may e…
AIR: Improving Agent Safety through Incident Response
Zibo Xiao, Jun Sun, Junjie Chen
Large Language Model (LLM) agents are increasingly deployed in practice across a wide range of autonomous applications. Yet current safety mechanisms for LLM agents focus almost ex…
TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
Qingchao Shen, Zibo Xiao, Lili Huang +3
Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to el…
SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
Haoyu Wang, Zibo Xiao, Yedi Zhang +2
LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the pot…
Optimization-Aware Test Generation for Deep Learning Compilers
Qingchao Shen, Zan Wang, Haoyang Ma +5
Deep Learning (DL) compilers have been widely utilized to optimize DL models for efficient deployment across various hardware. Due to their vital role in the DL ecosystem, ensuring…