Grasping Adversarial Attacks on Deep Convolutional Neural Networks for Cholangiocarcinoma Classification

Researchers have proposed plenty of novel deep convolutional neural networks (CNNs) architectures to achieve state-of-the-art performance in computer vision benchmarking datasets. Nevertheless, deep CNNs are still vulnerable to attacks such as adversarial attacks, which can effectively fool them. As...

Full description

Saved in:
Bibliographic Details
Main Authors: Diyasa, I Gede Susrama Mas, Wahid, Radical Rakhman, Amiruddin, Brilian Putra
Format: Conference Proceeding
Language:English
Subjects:
adversarial attacks
Biological system modeling
cholangiocarcinoma classification
Computational modeling
Computer architecture
computer vision
deep convolutional neural networks
Grasping
medical images
Medical services
Production
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Researchers have proposed plenty of novel deep convolutional neural networks (CNNs) architectures to achieve state-of-the-art performance in computer vision benchmarking datasets. Nevertheless, deep CNNs are still vulnerable to attacks such as adversarial attacks, which can effectively fool them. As a consequence, this attack will hinder the deployed model during production. Moreover, this fact causes a new obstacle towards the development of the future deep CNNs architecture, especially in some crucial fields, for instance, healthcare that uses deep learning to assist physicians in detecting disease from medical images. Since there are many novel adversarial attacks methods out there, this work evaluates the attack efficacy of various adversarial attacks methods against the model performance, specifically on the cholangiocarcinoma classification task. Intriguingly, from our experiment using several CNNs models, EfficientNet-BO gives the highest averaged accuracy after being attacked by some adversarial attack methods.
ISSN:2575-5145
DOI:10.1109/EHB52898.2021.9657589