Ping Liu

The paper introduces SEED, a large-scale benchmark dataset for tracing sequential deepfake facial edits, and proposes FAITH, a frequency-aware Transformer model that effectively detects and orders these cumulative editing events.

The paper introduces the Gaussian Privacy Protector (GPP), a framework that provides instance-level privacy for continuous data releases in federated learning by learning a stochastic encoder that sanitizes raw data while preserving utility.

The paper introduces Quantum Futures Interactive, a live, interdisciplinary demonstration platform designed to educate participants and facilitate dialogue on transitioning blockchain systems from classical to quantum-resilient security.

QSignAI is an open-source platform that integrates quantum-randomness-seeded identity signatures into a conversational AI social messaging system, demonstrating a practical bidirectional link between AI and quantum science.

The paper proposes RPCASSM, a novel state space model leveraging Robust PCA (RPCA) to accurately detect and segment infrared small targets by separately modeling background and target information based on their unique spatial properties.