Results 261 to 270 of about 1,662,189 (295)

Extreme vulnerability to intruder attacks destabilizes network dynamics. [PDF]

Nat Commun
Nazerian A, Tangerami S, Asllani M, Phillips D, Makse H, Sorrentino F.   +5 more
europepmc   +1 more source

Toward leveraging intrinsic point cloud features in 3D adversarial attacks. [PDF]

PLoS One
Naderi H, Dinesh C, Bajić IV, Kasaei S.
europepmc   +1 more source

Self-healing neural networks via modular patch layers for diverse structural and adversarial damages. [PDF]

Sci Rep
Santhosh Reddy B, Deepa Nivethika S, Vara Anjan B, Mahidhar Reddy P, SenthilPandian M, Roobankumar R.   +5 more
europepmc   +1 more source

Air Target ISAR Recognition Based on Data Augmentation and Transfer Learning. [PDF]

Sensors (Basel)
Wang M, Huang Z, Cai J, Wu T, Lin Y.
europepmc   +1 more source

Lightweight Security-by-Design for TinyML Models in Constrained Embedded Environments. [PDF]

Sensors (Basel)
Alanazi HA, Alshammari KR.
europepmc   +1 more source

Automating the creation of fashion patterns using deep learning algorithms. [PDF]

Front Artif Intell
Alsabhi R.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Learning Universal Adversarial Perturbation by Adversarial Example

Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Deep learning models have shown to be susceptible to universal adversarial perturbation (UAP), which has aroused wide concerns in the community. Compared with the conventional adversarial attacks that generate adversarial samples at the instance level, UAP can fool the target model for different instances with only a single perturbation, enabling us to
Maosen Li, Yanhua Yang, Kun Wei, Xu Yang 0019, Heng Huang 0001   +4 more
openaire   +2 more sources