Skip to content
InfoResearchPeer-reviewed

SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack Against No-Reference Image Quality Assessment Models

Published
Record updated
View JSON

Summary

This paper presents SEGA, a transfer-based black-box attack against no-reference image quality assessment (NR-IQA) models. It approximates the target model's gradient by applying Gaussian smoothing to source models and ensembling their smoothed gradients, then uses a perturbation filter mask to keep the adversarial perturbations imperceptible. The authors report superior transferability compared with prior white-box-derived attacks, though the source text gives no specific figures.