Reversible Adversarial Examples with Minimalist Evolution for Recognition Control in Computer Vision

Reversible Adversarial Examples with Minimalist Evolution for Recognition Control in Computer Vision

As artificial intelligence increasingly automates the recognition and analysis of visual content, it poses significant risks to privacy, security, and autonomy. Computer vision systems can surveil and exploit data without consent. With these concerns in mind, we introduce a novel method to control w...

Full description

Saved in:
Bibliographic Details
Main Authors: Shilong Yang, Lu Leng, Ching-Chun Chang, Chin-Chen Chang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
data security
reversible data hiding
reversible adversarial example
dual-color space
black-box attack
Online Access:https://www.mdpi.com/2076-3417/15/3/1142
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items