← Search

Mohammad Mahdinur Rahman

2 accepted papers

2026

AutoDebias: An Automated Framework for Detecting and Mitigating Backdoor Biases in Text-to-Image Models

CVPR 2026

Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for natural statistical biases, struggle with these deliberate and su

Cited by 0SourcecodeScholar
2025

Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning

EMNLP 2025

The effectiveness of instruction fine-tuning for Large Language Models is fundamentally constrained by the quality and efficiency of training datasets. This work introduces Low-Confidence Gold (LCG), a novel filtering framework that employs centroid-based clustering and confidence-guided selection f