Robust Federated Learning with Adaptable Learning Rate

Jingxuan, Zhou; Zhong, Zhengyi; Wang, Ji; Zhang, Xiongtao; Chen, Fuxu; Chun, Youngsub

doi:10.1109/bigdia53151.2021.9619731

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) How to improve the defense performances during the aggregation phase: The defense during the aggregation phase involves filtering out poisoned updates after they have been received by the aggregator [230], [249], [250]. Some defense methodologies at this stage use historical information to train a filter that can identify the backdoor in the original global model.…”

Section: B Defense Methods In Wflmentioning

confidence: 99%

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Wang

Qiao

Zhang

et al. 2022

2022 IEEE Wireless Communications and Networking Conference (WCNC)

View full text Add to dashboard Cite

Due to the greatly improved capabilities of devices, massive data, and increasing concern about data privacy, Federated Learning (FL) has been increasingly considered for applications to wireless communication networks (WCNs). Wireless FL (WFL) is a distributed method of training a global deep learning model in which a large number of participants each train a local model on their training datasets and then upload the local model updates to a central server. However, in general, nonindependent and identically distributed (non-IID) data of WCNs raises concerns about robustness, as a malicious participant could potentially inject a "backdoor" into the global model by uploading poisoned data or models over WCN. This could cause the model to misclassify malicious inputs as a specific target class while behaving normally with benign inputs. This survey provides a comprehensive review of the latest backdoor attacks and defense mechanisms. It classifies them according to their targets (data poisoning or model poisoning), the attack phase (local data collection, training, or aggregation), and defense stage (local training, before aggregation, during aggregation, or after aggregation). The strengths and limitations of existing attack strategies and defense mechanisms are analyzed in detail. Comparisons of existing attack methods and defense designs are carried out, pointing to noteworthy findings, open challenges, and potential future research directions related to security and privacy of WFL.

show abstract

Section: B Defense Methods In Wflmentioning

confidence: 99%

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Wang

Qiao

Zhang

et al. 2022

2022 IEEE Wireless Communications and Networking Conference (WCNC)

View full text Add to dashboard Cite

show abstract

“…Su [177] proposes an adaptive learning path recommendation system for e-learning that outperforms other approaches, using a novel hybrid approach based on fuzzy Delphi method, fuzzy ISM, and Kelly Repertory Grid Technology. Zhou et al [208] provides a new insight into the non-convergence issue of Adam, an adaptive learning rate method, proposing a novel method called AdaShift that decorrelates gradient and second-moment terms to address the non-convergence problem while maintaining competitive performance. Huang, Yang and Lawrence [74] proposes a classification-based approach to improve the accuracy and reduce the computational complexity of data mining-based concept map generation in adaptive learning systems.…”

Section: A Cluster Of General Concepts Of Adaptive Learning In E-lear...mentioning

confidence: 99%

Adaptive learning: a cluster-based literature review (2011-2022)

Fadieieva

2023

Educ. Technol. Q.

View full text Add to dashboard Cite

Adaptive learning is a personalized instruction system that adjusts to the needs, preferences, and progress of learners. This paper reviews the current and future developments of adaptive learning in higher education, especially in relation to the digital education strategy of the European Union. It also uses a cluster analysis framework to explore the main themes and their relationships in the academic literature on adaptive learning. The paper highlights the potential of emerging technologies such as AI, eye-tracking, and physiological measurements to improve the personalization and effectiveness of adaptive learning systems. It presents various methods, algorithms, and prototypes that incorporate learning styles into adaptive learning. It also stresses the importance of continuous professional development in e-learning, media literacy, computer security, and andragogy for teachers who use adaptive learning systems. The paper concludes that adaptive learning can promote creativity, innovation, and lifelong learning in Ukrainian higher education, but it also acknowledges the challenges and suggests further research to assess its impact.

show abstract

Robust Federated Learning with Adaptable Learning Rate

Cited by 2 publications

References 4 publications

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Adaptive learning: a cluster-based literature review (2011-2022)

Contact Info

Product

Resources

About