4 papers
pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation
Zonghao Ying, Xiangfan Wu, Bo Yang +5
Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pik…
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
Yong Yang, Xing Zheng, Huiyu Wu +7
The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and the language models themselves, h…
Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
Liang Zhu, Minyang Hu, Bo Yang +6
Computation cost is a critical challenge for LLM agent systems, as their long-horizon trajectories continuously accumulate computational overhead. While existing studies focus on i…
PolyLink: A Blockchain Based Decentralized Edge AI Platform for LLM Inference
Hongbo Liu, Jiannong Cao, Bo Yang +7
The rapid advancement of large language models (LLMs) in recent years has revolutionized the AI landscape. However, the deployment model and usage of LLM services remain highly cen…