Skip to content

Author

Khang Nguyen

We have 2 of 59 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Sep 2026

Switchable backdoor attack in vision transformers via progressive dual-token injection from shallow to deep layers

A novel progressive dual-token injection technique is proposed, in which two specially designed tokens are inserted from shallow to deep layers of the ViT model, aiming to mislead the model’s decision when a trigger appears in the input image.

D. M. Do, Khang Nguyen · 0 citations
Conference Aug 2026

Domain-Adaptive Object Detection via Pseudo-Label Self-Training and Depth Priors

Unsupervised Domain Adaptation (UDA) for object detection remains challenging under adverse weather due to significant distribution shifts. While recent Vision Foundation Model (VFM) based methods show promise, they often encounter limitations in extreme domain gaps and pseudo-label noise. This paper proposes two enhan...

T. Doan, D. C. Bui, Khanh-Duy Nguyen et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.