Defending Against Adversarial Fingerprint Attacks Based on Deep Image Prior
Recently, deep learning-based biometric authentication systems, especially fingerprint authentication, have been used widely in real-world. However, these systems are vulnerable to adversarial attacks which prevent deep learning models from distinguishing input data properly. To solve these problems...
Main Authors: | Hwajung Yoo, Pyo Min Hong, Taeyong Kim, Jung Won Yoon, Youn Kyu Lee |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10196440/ |
Similar Items
-
Real-Time Adversarial Attack Detection with Deep Image Prior Initialized as a High-Level Representation Based Blurring Network
by: Richard Evan Sutanto, et al.
Published: (2020-12-01) -
Performance Improvement of Image-Reconstruction-Based Defense against Adversarial Attack
by: Jungeun Lee, et al.
Published: (2022-07-01) -
Defending Adversarial Attacks against DNN Image Classification Models by a Noise-Fusion Method
by: Lin Shi, et al.
Published: (2022-06-01) -
DDSA: A Defense Against Adversarial Attacks Using Deep Denoising Sparse Autoencoder
by: Yassine Bakhti, et al.
Published: (2019-01-01) -
Defending against FakeBob Adversarial Attacks in Speaker Verification Systems with Noise-Adding
by: Zesheng Chen, et al.
Published: (2022-08-01)