Author

Baoyuan Wu

Observed name: Wu, Baoyuan

Institutions: Chinese University of Hong Kong, Chinese University of Hong Kong, Shenzhen

Observed institutions: Chinese University of Hong Kong, Chinese University of Hong Kong, Shenzhen

ORCID: 0000-0003-2183-5990

Observed ORCID: 0000-0003-2183-5990

OpenAlex ID: A5125570039

Visual Adversarial Attacks and Defenses in the Physical World: A Survey

2026 · Xingxing Wei, Bangzheng Pu, et al. · ACM Computing Surveys · 5

Seeking Flat Minima Over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation

2026 · Meixi Zheng, Kehan Wu, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1

Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation

2026 · Wang, Ruotong, Zhu, Zihao, et al. · arXiv (Cornell University)

Adversarial Machine Learning

2026 · Baoyuan Wu, Meixi Zheng · WORLD SCIENTIFIC eBooks

BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation

2026 · Zihao Zhu, Ruotong Wang, et al.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals

2026 · Liu, Aoxi, Chen, Yupeng, et al. · arXiv (Cornell University)

Adversarial Fine-Tuning on Speech Foundation Model with Vulnerable Attention Consistency Regularization for Robust Speech Recognition

2026 · Yanyun Wang, Baoyuan Wu, et al. · IEEE International Conference on Acoustics Speech and Signal Processing

Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework

2026 · Wu, Guanzong, Zhu, Zihao, et al. · arXiv (Cornell University)

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer

2026 · Chen, Yupeng, Yu, Junchi, et al. · arXiv (Cornell University)

Works count: 9

Citation count: 6

H-index: 1

I10-index: