Results 101 to 110 of about 4,795 (257)

Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Policy heterogeneity is crucial for achieving sophisticated coordination in complex collaborative tasks, which has emerged as one of the key challenges in multi‐agent reinforcement learning (MARL) in recent years. Notably, the grouping paradigm has made remarkable progress in addressing policy heterogeneity.
Yirui Liu, Xueqiang Gu, Caiming Zheng, Xin Xu, Zhangling Wang, Wanpeng Zhang, Yixing Lan   +6 more
wiley   +1 more source

RES‐AD: An AutoML‐Driven Robust Ensemble Framework for Real‐Time Anomaly Detection and Energy Forecasting in Smart Grids

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Accurate load forecasting and reliable anomaly detection are critical for the stable operation of modern smart grids (SGs), which increasingly rely on cyber‐connected infrastructures. However, the integration of smart metres and two‐way communication exposes SGs to data integrity attacks that can manipulate consumption measurements, degrade ...
Murad Ali Khan, Naeem Iqbal, Syed Shehryar Ali Naqvi, Muhammad Faseeh, Do‐Hyeun Kim   +4 more
wiley   +1 more source

CMDN: Pre-Trained Visual Representations Boost Adversarial Robustness for UAV Tracking

Drones
Visual object tracking is widely adopted to unmanned aerial vehicle (UAV)-related applications, which demand reliable tracking precision and real-time performance.
Ruilong Yu, Zhewei Wu, Qihe Liu, Shijie Zhou, Min Gou, Bingchen Xiang   +5 more
doaj   +1 more source

Robust Multi‐Source Batch Normalisation for Test‐Time Batch Adaptation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Test‐Time Batch Adaptation (TTBA) aims to adapt a pre‐trained source model to small, unlabelled target batches at test time. The TTBA methods focus on adapting the pre‐trained model or the target data in a one‐to‐one alignment paradigm. However, these one‐to‐one alignment paradigms assume that the source domain may share the same knowledge ...
Xinlin Xiao, Xiangtao Zheng, Jianhua Tao, Xiaoqiang Lu   +3 more
wiley   +1 more source

PPEPV‐RDL: Achieving Privacy‐Preserving, Efficient, Publicly Verifiable Rational Delegation Learning

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Delegation learning is an implementation approach within privacy‐preserving machine learning (PPML). It refers to that the delegator outsources the training task to servers with strong computing power due to its own limited computing resources, and the servers return the correct training results and get the service revenue.
Xinyu Zhang, Zerui Chen, Youliang Tian, Jinbo Xiong, Jianfeng Ma   +4 more
wiley   +1 more source

Detection and Defense: Student-Teacher Network for Adversarial Robustness

IEEE Access
Defense against adversarial attacks is critical for the reliability and safety of deep neural networks (DNNs). Current state-of-the-art defense methods achieve significant robustness against adversarial attacks.
Kyoungchan Park, Pilsung Kang
doaj   +1 more source

Looking at quality through a systems lens—Applying systems thinking to the Australian National Disability Insurance Scheme

Australian Journal of Public Administration, EarlyView.
ABSTRACT It is widely recognised that many policy systems are complex, requiring collaboration across different organisations and sectors to address socioeconomic outcomes and inequalities. Yet, the public policy literature is dominated by rational–technical frameworks that struggle to understand complex systems. This paper applies ideas from the field
Jade Hart, Vindhya Weeratunga, Helen Dickinson, Deborah Blackman   +3 more
wiley   +1 more source

Generalization of Defense Effects Learned from a Single Adversarial Attack

Computation
Adversarial attacks misled deep neural networks by injecting perturbations into input images. Training networks with adversarial examples defended against adversarial attacks. However, training with specific adversarial examples only defended against the
Dongxian Niu, Lin Shi
doaj   +1 more source

How Leaders With Dark Personality Shape Their Climates: Developing a Theory of Influence Tactics and Follower Responses

British Journal of Management, EarlyView.
Abstract Despite burgeoning attention to dark leaders, we lack understanding about how they shape their climates. Using the dark triad (Machiavellianism, narcissism, psychopathy), we integrate social psychology and leadership research on interpersonal, romantic and leader–follower relationships to identify two predominant influence strategies ...
Al‐Karim Samnani, Sadia Jahanzeb
wiley   +1 more source

Adversarial Attacks and Defenses in Fault Detection and Diagnosis: A Comprehensive Benchmark on the Tennessee Eastman Process

IEEE Open Journal of the Industrial Electronics Society
Integrating machine learning into Automated Control Systems (ACS) enhances decision-making in industrial process management. One of the limitations to the widespread adoption of these technologies in industry is the vulnerability of neural networks to ...
Vitaliy Pozdnyakov, Aleksandr Kovalenko, Ilya Makarov, Mikhail Drobyshevskiy, Kirill Lukyanov   +4 more
doaj   +1 more source