Author

Arian Komaei Koma

2 papers 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

Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models

Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts from Text-to-Image (T2I) models without prohibitive retraining. However, we reveal that current state-of-the-art (SOTA) approaches are brittle due to a severe lack of robustness to noise initialization. We call this phenome...

Arian Komaei Koma, Seyed Amir Kasaei, Aida Aryafar et al. · 0 citations

#artificial intelligence May 2026

Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models

BEAP is introduced, a black-box, embedding-aware adversarial prompting attack that leverages a large language model (LLM) to iteratively generate effective adversarial prompts and exploit such hidden vulnerabilities.

Arian Komaei Koma, Seyed Amir Kasaei, A. M. Sadeghzadeh et al. · arXiv.org · 1 citation