Results 271 to 280 of about 1,662,189 (295)

Understanding adversarial robustness against on-manifold adversarial examples

Pattern Recognition
Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of the adversarial examples is the off-manifold assumption: adversarial examples lie off the data manifold. However, recent research showed
Yanbo Fan, Zhi-Quan Tom Luo
exaly   +3 more sources

Some of the next articles are maybe not open access.

Related searches:

On The Generation of Unrestricted Adversarial Examples

2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2020
Adversarial examples are inputs designed by an adversary with the goal of fooling the machine learning models. Most of the research about adversarial examples have focused on perturbing the natural inputs with the assumption that the true label remains unchanged.
Mehrgan Khoshpasand, Ali A. Ghorbani 0001   +1 more
openaire   +1 more source

Curse of Dimensionality in Adversarial Examples

2019 International Joint Conference on Neural Networks (IJCNN), 2019
While machine learning and deep neural networks in particular, have undergone massive progress in the past years, this ubiquitous paradigm faces a relatively newly discovered challenge, adversarial attacks. An adversary can leverage a plethora of attacking algorithms to severely reduce the performance of existing models, therefore threatening the use ...
Nandish Chattopadhyay, Anupam Chattopadhyay, Sourav Sen Gupta 0001, Michael Kasper   +3 more
openaire   +1 more source

On the Salience of Adversarial Examples

2019
Adversarial examples are beginning to evolve as rapidly as the deep learning models they are designed to attack. These intentionally-manipulated inputs attempt to mislead the targeted model while maintaining the appearance of innocuous input data. Countermeasures against these attacks that take a global approach tend to be lossy to the original data ...
openaire   +2 more sources

Adversarial Examples for Malware Detection

2017
Machine learning models are known to lack robustness against inputs crafted by an adversary. Such adversarial examples can, for instance, be derived from regular inputs by introducing minor—yet carefully selected—perturbations.
Kathrin Grosse, Nicolas Papernot, Praveen Manoharan, Michael Backes, Patrick McDaniel   +4 more
openaire   +1 more source

Advops: Decoupling Adversarial Examples

Pattern Recognition, 2023
Donghua Wang 0001, Wen Yao 0001, Tingsong Jiang, Xiaoqian Chen   +3 more
openaire   +2 more sources

Learning defense transformations for counterattacking adversarial examples

Neural Networks, 2023
Shuhai Zhang, Tan Mingkui
exaly  

Generating adversarial examples via enhancing latent spatial features of benign traffic and preserving malicious functions

Neurocomputing, 2022
JingWei Hao
exaly  

Assessing the Threat of Adversarial Examples on Deep Neural Networks for Remote Sensing Scene Classification: Attacks and Defenses

IEEE Transactions on Geoscience and Remote Sensing, 2021
Liangpei Zhang, Bo Du, Yonghao Xu
exaly  

EnsembleFool: A method to generate adversarial examples based on model fusion strategy

Computers and Security, 2021
Ruxin Wang, Renyang Liu
exaly