Results 91 to 100 of about 94,262 (290)

An adversarial attack method based on pixel location characteristics

Journal of Intelligent Systems
Deep learning techniques have been widely used in various fields. However, they face significant security challenges due to the existence of adversarial examples.
Zhao Qin, Liu Jiuhong, Ma Xian, Liu Tongbo, Du Yingzhen   +4 more
doaj   +1 more source

Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

, 2018
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications.
Liu, Yannan, Luo, Bo, Wei, Lingxiao, Xu, Qiang   +3 more
core   +1 more source

Sparse Adversarial Attack in Multi-agent Reinforcement Learning [PDF]

, 2022
Yizheng Hu, Zhihua Zhang
openalex   +1 more source

Machine Learning and Artificial Intelligence Techniques for Intelligent Control and Forecasting in Energy Storage‐Based Power Systems

Energy Science &Engineering, EarlyView.
A new energy paradigm assisted by AI. ABSTRACT The tremendous penetration of renewable energy sources and the integration of power electronics components increase the complexity of the operation and power system control. The advancements in Artificial Intelligence and machine learning have demonstrated proficiency in processing tasks requiring ...
Balasundaram Bharaneedharan, Suresh Panchanathan, Chan Choon Kit, Elumalai Perumal Venkatesan, Nasim Hasan   +4 more
wiley   +1 more source

Ctta: a novel chain-of-thought transfer adversarial attacks framework for large language models

Cybersecurity
Recent studies have indicated that large language models (LLMs) remain susceptible to adversarial attacks, despite enhanced robustness through the chain-of-thought (CoT) capability.
Xinxin Yue, Zhiyong Zhang, Junchang Jing, Weiguo Wang   +3 more
doaj   +1 more source

Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks [PDF]

, 2023
Erfan Darzi, Nanna M. Sijtsema, P. M. A van Ooijen   +2 more
openalex   +1 more source

Caught in the fire: An accidental ethnography of discomfort in researching sex work

Feminist Anthropology, EarlyView.
Abstract Drawing on fifteen years of engagement with researching Israel's sex industry, this article uses accidental ethnography to propose discomfort‐as‐method for feminist anthropology. I argue that discomfort is not a by‐product of fieldwork but a constitutive condition that disciplines researchers and shapes what can be known.
Yeela Lahav‐Raz
wiley   +1 more source

Organoids and organ‐on‐a‐chip models for investigating the pathophysiology of the human reproductive system

Interdisciplinary Medicine, EarlyView.
Organoids and organ‐on‐a‐chips are advancing reproductive system research. In the female reproductive system, applications include cancer organoid models, placental chips, and hormone simulation models. For the male reproductive system, research focuses on drug resistance mechanisms, co‐culture platforms, and infertility studies. These refined in vitro
Hongqi Zhang, Shiwen Deng, Fangfang Jin, Jiayao Qu, Xiang Fan, Peng Chen, Xinrong Fan   +6 more
wiley   +1 more source

Preparing for Tomorrow's Teamwork: Insights From eSports on How Human Expertise Shapes Training Needs for AI‐Integrated Work

Journal of Organizational Behavior, EarlyView.
ABSTRACT As organizations increasingly adopt human‐AI teams (HATs), understanding how to enhance team performance is paramount. A crucially underexplored area for supporting HATs is training, particularly helping human teammates to work with these inorganic counterparts.
Caitlin M. Lancaster, Christopher Flathmann, Jennifer Hsu, Nathan J. McNeese, Thomas A. O'Neill, Eduardo Salas   +5 more
wiley   +1 more source

DIPA: Adversarial Attack on DNNs by Dropping Information and Pixel-Level Attack on Attention

Information
Deep neural networks (DNNs) have shown remarkable performance across a wide range of fields, including image recognition, natural language processing, and speech processing. However, recent studies indicate that DNNs are highly vulnerable to well-crafted
Jing Liu, Huailin Liu, Pengju Wang, Yang Wu, Keqin Li   +4 more
doaj   +1 more source