5 papers
Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
Yujie Ma, Jialin Rong, Chenxi Yang +5
Large Language Models (LLMs) have been actively integrated into modern software systems as critical components, introducing a new type of software vulnerability, LLM-in-the-Loop (L…
Privacy-Enhancing Encryption in Data Sharing: A Survey on Security, Performance and Functionality
Yongyang Lv, Xiaohong Li, Ruitao Feng +5
The vigorous development of the Internet has spurred exponential data growth, yet data is predominantly stored in isolated user entities, hampering its full value realization. In l…
DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
Yu Li, Qiang Hu, Yao Zhang +3
Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent,…
UncertaintyZoo: A Unified Toolkit for Quantifying Predictive Uncertainty in Deep Learning Systems
Xianzong Wu, Xiaohong Li, Lili Quan +1
Large language models(LLMs) are increasingly expanding their real-world applications across domains, e.g., question answering, autonomous driving, and automatic software developmen…
Understanding the Supply Chain and Risks of Large Language Model Applications
Yujie Ma, Lili Quan, Xiaofei Xie +4
The rise of Large Language Models (LLMs) has led to the widespread deployment of LLM-based systems across diverse domains. As these systems proliferate, understanding the risks ass…