Results 1 to 10 of about 219,753 (266)

Avoiding catastrophic overfitting in fast adversarial training with adaptive similarity step size. [PDF]

PLoS ONE
Adversarial training has become a primary method for enhancing the robustness of deep learning models. In recent years, fast adversarial training methods have gained widespread attention due to their lower computational cost.
Jie-Chao Zhao, Jin Ding, Yong-Zhi Sun, Ping Tan, Ji-En Ma, You-Tong Fang   +5 more
doaj   +2 more sources

Adversarial Robustness Enhancement for Deep Learning-Based Soft Sensors: An Adversarial Training Strategy Using Historical Gradients and Domain Adaptation [PDF]

Sensors
Despite their high prediction accuracy, deep learning-based soft sensor (DLSS) models face challenges related to adversarial robustness against malicious adversarial attacks, which hinder their widespread deployment and safe application.
Runyuan Guo, Qingyuan Chen, Han Liu, Wenqing Wang   +3 more
doaj   +2 more sources

Adversarial Training Methods for Deep Learning: A Systematic Review

Algorithms, 2022
Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms.
Weimin Zhao, Sanaa Alwidian, Qusay H. Mahmoud   +2 more
doaj   +3 more sources

STS-AT: A Structured Tensor Flow Adversarial Training Framework for Robust Intrusion Detection [PDF]

Sensors
Network intrusion detection is a key technology for ensuring cybersecurity. However, current methods face two major challenges: reliance on manual feature engineering, which leads to the loss of discriminative information, and the vulnerability of deep ...
Juntong Zhu, Zhihao Chen, Rong Cong, Hongyu Sun, Yanhua Dong   +4 more
doaj   +2 more sources

On the Effectiveness of Adversarial Training in Defending against Adversarial Example Attacks for Image Classification

Applied Sciences, 2020
State-of-the-art neural network models are actively used in various fields, but it is well-known that they are vulnerable to adversarial example attacks.
Sanglee Park, Jungmin So
doaj   +3 more sources

Lightweight defense mechanism against adversarial attacks via adaptive pruning and robust distillation

网络与信息安全学报, 2022
Adversarial training is one of the commonly used defense methods against adversarial attacks, by incorporating adversarial samples into the training process.However, the effectiveness of adversarial training heavily relied on the size of the trained ...
Bin WANG, Simin LI, Yaguan QIAN, Jun ZHANG, Chaohao LI, Chenming ZHU, Hongfei ZHANG
doaj   +3 more sources

Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition [PDF]

Sensors, 2021
Saeed Ur Rehman, Jamal Hussain Shah, Talha Meraj   +2 more
exaly   +2 more sources

Universal Adversarial Training Using Auxiliary Conditional Generative Model-Based Adversarial Attack Generation

Applied Sciences, 2023
While Machine Learning has become the holy grail of modern-day computing, it has many security flaws that have yet to be addressed and resolved. Adversarial attacks are one of these security flaws, in which an attacker appends noise to data samples that ...
Hiskias Dingeto, Juntae Kim
doaj   +1 more source

Structure Estimation of Adversarial Distributions for Enhancing Model Robustness: A Clustering-Based Approach

Applied Sciences, 2023
In this paper, we propose an advanced method for adversarial training that focuses on leveraging the underlying structure of adversarial perturbation distributions. Unlike conventional adversarial training techniques that consider adversarial examples in
Bader Rasheed, Adil Khan, Asad Masood Khattak   +2 more
doaj   +1 more source

AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks Through Accuracy Gradient

IEEE Access, 2022
Adversarial training is exploited to develop a robust Deep Neural Network (DNN) model against the malicious altered data. These attacks may have catastrophic effects on DNN models but are indistinguishable for a human being.
Farzad Nikfam, Alberto Marchisio, Maurizio Martina, Muhammad Shafique   +3 more
doaj   +1 more source