Li Xiong

The paper introduces AutoMIA, a novel framework that uses LLM agents to automate the discovery and implementation of Membership Inference Attacks (MIAs), achieving state-of-the-art performance by systematically exploring attack strategies.

The paper proposes QShield, a hybrid quantum-classical neural network architecture, which significantly enhances the adversarial robustness of deep learning models against various attacks.

The paper introduces $(l, b)$-inextractability, a new formal measure that demonstrates that standard indistinguishability properties are insufficient for guaranteeing protection against data extraction from LLM APIs.