Results 111 to 120 of about 6,370 (239)

Adversarial Attacks on Variational Autoencoders

CoRR, 2018
Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We assess --- with statistically validated experiments --- the resistance to attacks of three variational ...
George Gondim-Ribeiro, Pedro Tabacof, Eduardo Valle   +2 more
openaire   +2 more sources

APTNet: A Condition‐Sensitive Modulation Framework for Surface Pressure Prediction on Supersonic Aircraft

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Accurate surface‐pressure prediction over broad operating envelopes is critical for supersonic aerodynamic analysis and design. To overcome the bottlenecks of traditional computational fluid dynamics (CFD) in real‐time performance and computational efficiency, data‐driven deep learning methods have emerged. However, existing data‐driven models
Hongbin Xu, Yin Long, Junlin Wu
wiley   +1 more source

Adversarial Attack and Defense in Breast Cancer Deep Learning Systems. [PDF]

Bioengineering (Basel), 2023
Li Y, Liu S.
europepmc   +1 more source

‘Pro‐Germans in the Pulpits’: The Queensland Presbyterian Church and the Great War

Journal of Religious History, EarlyView.
During World War I, Protestant churches in Australia, on the whole, enthusiastically supported the war effort. The Queensland Presbyterian Church was a significant exception. This study analyses discord and tensions among its clergymen about what constituted an appropriate response to the war.
Mark Cryle
wiley   +1 more source

Image classification adversarial attack with improved resizing transformation and ensemble models. [PDF]

PeerJ Comput Sci, 2023
Li C, Zhang H, Yang B, Wang J.
europepmc   +1 more source

Adversarial Attacks on Data Attribution

CoRR
Accepted at the 13th International Conference on Learning Representations (ICLR 2025)
Xinhe Wang 0001, Pingbang Hu, Junwei Deng, Jiaqi W. Ma   +3 more
openaire   +3 more sources

Who Is a Patriotic Man? Rethinking Hegemonic Masculinity in Modern Iran

Gender &History, EarlyView.
ABSTRACT This article examines the analytical viability of the concept of “hegemonic masculinity” in the historical study of masculinities in early‐twentieth‐century Iran (c.1890–1941). It argues that a radical problematizing of the concepts of hegemony, class, “the West,” and patriotism helps us move beyond the binaries of Western‐Iranian and modern ...
Ali Hashemian
wiley   +1 more source

Perturbing BEAMs: EEG adversarial attack to deep learning models for epilepsy diagnosing. [PDF]

BMC Med Inform Decis Mak, 2023
Yu J, Qiu K, Wang P, Su C, Fan Y, Cao Y.
europepmc   +1 more source

The company you keep: The influence of popular delinquents and deviant brokers on offending trajectories

Criminology, EarlyView.
Abstract Research on how delinquent peer associations affect individuals’ life courses is limited. This paper addresses this gap by examining delinquent peer network characteristics and their impact on offending trajectories through social network analysis (SNA) and group‐based trajectory modeling (GBTM).
Daniel Trovato
wiley   +1 more source

A Security Study of Multimodel Artificial Intelligence System: Adaptive Retention Attack for Object Detection System with Multifocus Image Fusion Model

Advanced Intelligent Systems
Image preprocessing models are usually employed as the preceding operations of high‐level vision tasks to improve the performance. The adversarial attack technology makes both these models face severe challenges.
Xueshuai Gao, Xin Jin, Shengfa Miao, Qian Jiang, Yunyun Dong, Wei Zhou, Shaowen Yao   +6 more
doaj   +1 more source