7 papers
FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness
Pianran Guo, Pengcheng Zhou, Yucheng Jian +4
Financial multimodal reasoning requires agents to coordinate numerical computation, retrieval, visual interpretation, and temporal grounding across heterogeneous evidence sources.…
DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
Pengcheng Zhou, Pianran Guo, Shuhua Chen +3
The growing use of information hiding in network streaming media for covert communication poses a significant security threat, necessitating the development of robust detection tec…
You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
Ching-Yu Kao, Xinfeng Li, Shenyu Dai +4
High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are gr…
Provably Secure Retrieval-Augmented Generation
Pengcheng Zhou, Yinglun Feng, Zhongliang Yang
Although Retrieval-Augmented Generation (RAG) systems have been widely applied, the privacy and security risks they face, such as data leakage and data poisoning, have not been sys…
Why do AI agents communicate in human language?
Pengcheng Zhou, Yinglun Feng, Halimulati Julaiti +1
Large Language Models (LLMs) have become foundational to modern AI agent systems, enabling autonomous agents to reason and plan. In most existing systems, inter-agent communication…
Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
Pengcheng Zhou, Yinglun Feng, Zhongliang Yang
The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their propriet…