Results 41 to 50 of about 79,918 (254)

Stochastic Substitute Training: A Gray-box Approach to Craft Adversarial Examples Against Gradient Obfuscation Defenses

, 2018
It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input.
Athalye Anish, Baluja Shumeet, Buckman Jacob, Diederik, Eykholt Kevin, Goodfellow Ian J, He Kaiming, Kurakin Alexey, Lin Min, Liu Yanpei, Lu Jiajun, Madry Aleksander, Metzen Jan Hendrik, Papernot Nicolas, Papernot Nicolas, Samangouei Pouya, Schulman John, Simonyan Karen, Tramèr Florian   +18 more
core   +1 more source

Adversarial Attack and Defense on Deep Neural Network-Based Voice Processing Systems: An Overview

Applied Sciences, 2021
Voice Processing Systems (VPSes), now widely deployed, have become deeply involved in people’s daily lives, helping drive the car, unlock the smartphone, make online purchases, etc.
Xiaojiao Chen, Sheng Li, Hao Huang
doaj   +1 more source

GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier

, 2019
Machine learning models, especially neural network (NN) classifiers, are widely used in many applications including natural language processing, computer vision and cybersecurity.
Khalil, Issa, Khreishah, Abdallah, Liu, Guanxiong   +2 more
core   +3 more sources

Adversarial Ranking Attack and Defense [PDF]

, 2020
Deep Neural Network (DNN) classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this paper, we propose two attacks against deep ranking systems, i.e., Candidate Attack and Query Attack, that can ...
Zhou, Mo, Niu, Zhenxing, Wang, Le, Zhang, Qilin, Hua, Gang   +4 more
openaire   +2 more sources

From the Discovery of the Giant Magnetocaloric Effect to the Development of High‐Power‐Density Systems

Advanced Materials Technologies, EarlyView.
The article overviews past and current efforts on caloric materials and systems, highlighting the contributions of Ames National Laboratory to the field. Solid‐state caloric heat pumping is an innovative method that can be implemented in a wide range of cooling and heating applications.
Agata Czernuszewicz, Yaroslav Mudryk, Jun Cui, Lucas Griffith, Duane D. Johnson, Julie Slaughter   +5 more
wiley   +1 more source

Survey on adversarial attacks and defenses for object detection

Tongxin xuebao, 2023
In response to recent developments in adversarial attacks and defenses for object detection, relevant terms and concepts associated with object detection and adversarial learning were first introduced.Subsequently, according to the evolution process of ...
Xinxin WANG, Jing CHEN, Kun HE, Zijun ZHANG, Ruiying DU, Qiao LI, Jisi SHE   +6 more
doaj   +2 more sources

A Mask-Based Adversarial Defense Scheme

Algorithms, 2022
Adversarial attacks hamper the functionality and accuracy of deep neural networks (DNNs) by meddling with subtle perturbations to their inputs. In this work, we propose a new mask-based adversarial defense scheme (MAD) for DNNs to mitigate the negative ...
Weizhen Xu, Chenyi Zhang, Fangzhen Zhao, Liangda Fang   +3 more
doaj   +1 more source

Information Transmission Strategies for Self‐Organized Robotic Aggregation

Advanced Robotics Research, EarlyView.
In this review, we discuss how information transmission influences the neighbor‐based self‐organized aggregation of swarm robots. We focus specifically on local interactions regarding information transfer and categorize previous studies based on the functions of the information exchanged.
Shu Leng, Zihan Li, Yifeng Shao, Jinhao Liu, Li Yu, Shuguang Li   +5 more
wiley   +1 more source

You Can’t Fool All the Models: Detect Adversarial Samples via Pruning Models

IEEE Access, 2021
Many adversarial attack methods have investigated the security issue of deep learning models. Previous works on detecting adversarial samples show superior in accuracy but consume too much memory and computing resources.
Renxuan Wang, Zuohui Chen, Hui Dong, Qi Xuan   +3 more
doaj   +1 more source

Defense-VAE: A Fast and Accurate Defense Against Adversarial Attacks [PDF]

, 2020
Deep neural networks (DNNs) have been enormously successful across a variety of prediction tasks. However, recent research shows that DNNs are particularly vulnerable to adversarial attacks, which poses a serious threat to their applications in security-sensitive systems.
Li, Xiang, Ji, Shihao
openaire   +2 more sources