← Search

Minji Son

2 accepted papers

2025

SAFIRE: Segment Any Forged Image Region

AAAI 2025technical

Most techniques approach the problem of image forgery localization as a binary segmentation task, training neural networks to label original areas as 0 and forged areas as 1. In contrast, we tackle this issue from a more fundamental perspective by partitioning images according to their originating s…

2023

Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models

ICCV 2023poster

As video analysis using deep learning models becomes more widespread, the vulnerability of such models to adversarial attacks is becoming a pressing concern. In particular, Universal Adversarial Perturbation (UAP) poses a significant threat, as a single perturbation can mislead deep learning model…

Cited by 6PDFScholar