Results 211 to 220 of about 94,262 (290)
Should all Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness
Journal of Geophysical Research: Machine Learning and Computation, Volume 3, Issue 1, February 2026.Abstract Geophysical data collected from active field sites are often contaminated by complex and heterogeneous noise, obscuring weak seismic events, and complicating automated interpretation. Although deep learning offers promising solutions for seismic processing, its performance is highly sensitive to the nature of training noise, especially under ...
S. Alsinan +4 more
wiley +1 more source
Space Weather, Volume 24, Issue 2, February 2026.Abstract This study investigates the effects of quiet time ionospheric conditions and the number of storm events used for training on the prediction of ionospheric total electron content (TEC) during geomagnetic storms using a deep learning method.
Se‐Heon Jeong +4 more
wiley +1 more source
How Mexican judicial reforms may have fueled crime: Arrest trends and trust erosion
Criminology &Public Policy, Volume 25, Issue 1, Page 89-112, February 2026.Abstract Background Mexico rolled out state‐led criminal justice reforms between 2000 and 2017 to modernize procedures and improve rule of law. Whether these changes reduced violent crime—especially in cartel‐affected areas—remains uncertain. Aims Estimate the impact of reform implementation on homicides and arrests, and assess mechanisms related to ...
Catalina Amuedo‐Dorantes +1 more
wiley +1 more source
Political Psychology, Volume 47, Issue 1, February 2026.Abstract In collective punishment, a group as a whole receives negative consequences because of the actions of a few. We argue that collective punishments lead to ingroup cohesiveness and adverse intergroup relations by instigating a punishment‐revenge cycle.
Mete Sefa Uysal +2 more
wiley +1 more source
Moral disagreements: Unearthing pathways to constructive and destructive behavioral responses
Political Psychology, Volume 47, Issue 1, February 2026.Abstract Issues like transgender rights often provoke strong emotional reactions, leading to polarized conflicts. Moral psychology suggests that emotions like anger and disgust drive destructive behaviors, such as avoiding or insulting the opponent. However, we argue that constructive behaviors, such as listening to the opponent, are also possible.
Bhakti Khati +3 more
wiley +1 more source
Securing Deep Neural Nets against Adversarial Attacks with Moving Target Defense. [PDF]
, 2017 Sailik Sengupta +2 more
openalex
Adversarial Attack for Explanation Robustness of Rationalization Models [PDF]
Yuankai Zhang +6 more
openalex +1 more source
Enhancing CT Segmentation Security against Adversarial Attack: Most Activated Filter Approach [PDF]
Woonghee Lee, Younghoon Kim
openalex +1 more source
Fast Adversarial Training against Textual Adversarial Attacks
Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates used by attackers are accessible, which is an ideal assumption.
Yang, Yichen, Liu, Xin, He, Kun
openaire +1 more source
Adversarial Attacks on Federated-Learned Adaptive Bitrate Algorithms
Rui-Xiao Zhang, Tianchi Huang
openalex +2 more sources