4 papers
AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
Peiran Wang, Yang Liu, Yunfei Lu +6
Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However,…
Black-box Optimization of LLM Outputs by Asking for Directions
Jie Zhang, Meng Ding, Yang Liu +2
We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks r…
PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
Yi Liu, Yang Liu, Leqian Zheng +5
With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries.…
What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis
Peiran Wang, Yang Liu, Yunfei Lu +2
Large language model (LLM) systems suffer from the models' unstable ability to generate valid and factual content, resulting in hallucination generation. Current hallucination dete…