Ning Zhang

This paper demonstrates that adversarial perturbations possess a low-rank structure, and proposes a two-step method to leverage this property to significantly improve the efficiency and effectiveness of black-box adversarial attacks.

The paper introduces a new dataset (SHDF) and a framework (T-AVFD) to robustly detect audio-visual deepfakes, specifically addressing the challenge posed by singing vocalizations.

MindZero introduces a self-supervised reinforcement learning framework that trains multimodal large language models (MLLMs) for efficient and robust online mental reasoning without requiring explicit mental state annotations.

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving state-of-the-art performance with reduced latency.

The paper proposes ST-DRC, a Spatial-Temporal Decoupled Reference Conditioning framework that effectively balances high-level semantic control and low-level identity fidelity for text-to-video generation.

This paper investigates how Generative AI enables scalable, hyper-realistic fraud in Chinese e-commerce by fabricating product defect evidence, proposing new defense mechanisms like verifiable material anchors.