Adversarial Examples for Image Cropping: Gradient-Based and Bayesian-Optimized Approaches for Effective Adversarial Attack

In this study, we propose novel approaches for generating adversarial examples targeting machine learning-based image cropping systems. Image cropping is crucial for meeting display space restrictions and highlighting content’s interest areas. However, existing image cropping systems often mi...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Masatomo Yoshida, Haruto Namura, Masahiro Okuda
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2024-01-01
Serija:	IEEE Access
Teme:	Adversarial examples image cropping object detection saliency map Twitter
Online dostop:	https://ieeexplore.ieee.org/document/10559590/
Oznake:	Označite Brez oznak, prvi označite!