Results 51 to 60 of about 34,476 (259)
Directional Adversarial Training for Robust Ownership-Based Recommendation System
IEEE Access, 2022 Machine learning algorithms are susceptible to cyberattacks, posing security problems in computer vision, speech recognition, and recommendation systems. So far, researchers have made great strides in adopting adversarial training as a defensive strategy.
Zhefu Wu +3 more
doaj +1 more source
Prior-Guided Adversarial Initialization for Fast Adversarial Training
, 2022 Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and dramatically decreases.
Xiaojun Jia +6 more
openaire +2 more sources
Improving Adversarial Robustness via Distillation-Based Purification
Applied Sciences, 2023 Despite the impressive performance of deep neural networks on many different vision tasks, they have been known to be vulnerable to intentionally added noise to input images.
Inhwa Koo, Dong-Kyu Chae, Sang-Chul Lee
doaj +1 more source
All‐Optical Reconfigurable Physical Unclonable Function for Sustainable Security
Advanced Materials, EarlyView.An all‐optical reconfigurable physical unclonable function (PUF) is demonstrated using plasmonic coupling–induced sintering of optically trapped gold nanoparticles, where Brownian motion serves as a robust entropy source. The resulting optical PUF exhibits high encoding density, strong resistance to modeling attacks, and practical authentication ...
Jang‐Kyun Kwak +4 more
wiley +1 more source
Increasing the Robustness of Image Quality Assessment Models Through Adversarial Training
TechnologiesThe adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-depth
Anna Chistyakova +6 more
doaj +1 more source
Inverse Design of Amorphous Materials With Targeted Properties
Advanced Materials, EarlyView.AMDEN is a diffusion model framework for the inverse design of amorphous materials with targeted properties. By incorporating Hamiltonian Monte Carlo refinement into the denoising process, the framework overcomes the challenge of generating thermally relaxed disordered structures.
Jonas A. Finkler +4 more
wiley +1 more source
Advanced Materials, EarlyView.This review summarizes the principles and challenges of nonaqueous lithium‐oxygen batteries and recent advances in cathode catalysts, including carbon‐based materials, metals, oxides, sulfides, nitrides, carbides, and redox mediators. It highlights emerging design strategies and artificial intelligence‐driven approaches, emphasizing data‐assisted ...
Yuqing Yao +8 more
wiley +1 more source
On the existence of solutions to adversarial training in multiclass classification
European Journal of Applied MathematicsAdversarial training is a min-max optimization problem that is designed to construct robust classifiers against adversarial perturbations of data. We study three models of adversarial training in the multiclass agnostic-classifier setting.
Nicolás García Trillos +2 more
doaj +1 more source
Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
IEEE Access, 2020 Deep Neural Networks (DNNs) classifiers performance degrades under adversarial attacks, such attacks are indistinguishably perturbed relative to the original data.
Benjamin Appiah +4 more
doaj +1 more source
A Robust Method to Protect Text Classification Models against Adversarial Attacks
Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022 Text classification is one of the main tasks in natural language processing. Recently, adversarial attacks have shown a substantial negative impact on neural network-based text classification models. There are few defenses to strengthen model predictions
BALA MALLIKARJUNARAO GARLAPATI +2 more
doaj +1 more source