Investigating the Transferability of TOG Adversarial Attacks in YOLO Models in the Maritime Domain

Investigating the Transferability of TOG Adversarial Attacks in YOLO Models in the Maritime Domain

In recent years, CNN-based object detectors have been widely adopted in autonomous systems. Although their capabilities are employed across various industries, these detectors are inherently susceptible to adversarial attacks. Despite extensive studies on their effects on image classification, adver...

Full description

Saved in:
Bibliographic Details
Main Authors: Phornphawit Manasut, Md Saleh Ibtasham, Zeynep Yaradanakul, Sepinoud Azimi, Sebastien Lafond, Bogdan Iancu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Maritime object detection
adversarial attacks
targeted objectness gradient (TOG) attack
adversarial attack transferability
Online Access:https://ieeexplore.ieee.org/document/11080415/
Tags: Add Tag
No Tags, Be the first to tag this record!
Login for hold and recall information

Internet

https://ieeexplore.ieee.org/document/11080415/

Similar Items