Author

Sadad Hasan

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.

Preprint Sep 2026

FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language Models

This work proposes textsc {FreqDoor], a training-time backdoor attack that implants triggers in the frequency domain for vision-language models (VLMs) and evaluates the attack on BLIP-2, InstructBLIP, and LLaVA for image captioning and visual question answering.

Yasir Arafat Prodhan, Sadad Hasan, Mohammed Imamul Hassan Bhuiyan · 0 citations