Skip to content

1 paper indexed here

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

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