Security of federated learning for cloud‐edge intelligence collaborative computing

Yang, Jie; Zheng, Jinhua; Zhang, Zheng; Chen, Q. I.; Wong, Duncan S.; Li, Yuanzhang

doi:10.1002/int.22992

Cited by 16 publications

(5 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The solution to this problem can meet the capacity requirements and minimize the service delay. Yang et al (2022) considered computing resources and bandwidth resources together, aiming at reducing the execution delay and the weighted sum of energy consumption of all users, and proposes an asynchronous deep reinforcement learning algorithm under cloud-edge collaboration to make relevant migration decisions. To meet the requirements of big data scenarios and the dynamic changes of the environment under edge nodes, the algorithm considers the computing power of both cloud computing and edge computing and can adaptively adjust the migration strategy.…”

Section: Related Workmentioning

confidence: 99%

Optimization design of railway logistics center layout based on mobile cloud edge computing

Zhang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

With the development of the economy, the importance of railway freight transportation has become essential. The efficiency of a railway logistics center depends on the types, quantities, information exchange, and layout optimization. Edge collaboration technology can consider the advantages of cloud computing’s rich computing storage resources and low latency. It can also provide additional computing power and real-time requirements for intelligent railway logistics construction. However, the cloud-side collaboration technology will introduce the wireless communication delay between the mobile terminal and the edge computing server. We designed a two-tier unloading strategy algorithm and solved the optimization problem by determining the unloading decision of each task. The cost of every task is calculated in the onboard device calculation, vehicular edge computing (VEC), and cloud computing server calculation. Simulation results show that the proposed method can save about 40% time delay compared to other unloading strategies.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimization design of railway logistics center layout based on mobile cloud edge computing

Zhang

2023

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…It has been proved that in the edge-case (or low-possibility sample), the backdoor-injected poisoned dataset can be irrelevant to the label description. For example, in the image classification application, the images of "Southwest airplane" are fed to the label of "truck" [33], [240]. Such implementation does decrease the dependency on the backdoored input design.…”

Section: A Backdoor Attacks On 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

“…Puthal et al 8 applied collaborative edge computing to smart villages. Considered the privacy protection issue of edge intelligence, FL provides an effective solution 9,10 . With the help of the cloud server, an intelligent edge‐cloud collaborative computing framework is constructed by training the collaborative model on the edge nodes of the industrial Internet of Things on a large scale 9,11,12 .…”

Section: Introductionmentioning

confidence: 99%

“…Considered the privacy protection issue of edge intelligence, FL provides an effective solution 9,10 . With the help of the cloud server, an intelligent edge‐cloud collaborative computing framework is constructed by training the collaborative model on the edge nodes of the industrial Internet of Things on a large scale 9,11,12 . However, we noticed that the FL framework via edge‐cloud collaboration is vulnerable to poisoning attacks in IoT application scenarios 13,14 .…”

Section: Introductionmentioning

confidence: 99%

“…9,10 With the help of the cloud server, an intelligent edge-cloud collaborative computing framework is constructed by training the collaborative model on the edge nodes of the industrial Internet of Things on a large scale. 9,11,12 However, we noticed that the FL framework via edge-cloud collaboration is vulnerable to poisoning attacks in IoT application scenarios. 13,14 Poisoning attacks include untargeted [15][16][17][18][19][20] and targeted attacks.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A federated learning attack method based on edge collaboration via cloud

et al. 2022

Self Cite

View full text Add to dashboard Cite

Federated learning (FL) is widely used in edge‐cloud collaborative training due to its distributed architecture and privacy‐preserving properties without sharing local data. FLTrust, the most state‐of‐the‐art FL defense method, is a federated learning defense system with trust guidance. However, we found that FLTrust is not very robust. Therefore, in the edge collaboration scenario, we mainly study the poisoning attack on the FLTrust defense system. Due to the aggregation rule, FLTrust, with trust guidance, the model updates of participants with a significant deviation from the root gradient direction will be eliminated, which makes the poisoning effect on the global model not obvious. To solve this problem, under the premise of not being deleted by the FLTrust aggregation rules, we construct malicious model updates that deviate from the trust gradient to the greatest extent to achieve model poisoning attacks. First, we utilize the rotation of high‐dimensional vectors around axes to construct malicious vectors with fixed orientations. Second, the malicious vector is constructed by the gradient inversion method to achieve an efficient and fast attack. Finally, a method of optimizing random noise is used to construct a malicious vector with a fixed direction. Experimental results show that our attack method reduces the model accuracy by 20%, severely undermining the usability of the model. Attacks are also successful hundreds of times faster than the FLTrust adaptive attack method.

show abstract

Security of federated learning for cloud‐edge intelligence collaborative computing

Cited by 16 publications

References 56 publications

Optimization design of railway logistics center layout based on mobile cloud edge computing

Optimization design of railway logistics center layout based on mobile cloud edge computing

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

A federated learning attack method based on edge collaboration via cloud

Contact Info

Product

Resources

About