Accurate Differentially Private Deep Learning on the Edge

Han, Rui; Li, Dong; Ouyang, Junyan; Liu, Chi Harold; Wang, Guoren; Wu, Dapeng; Chen, Lydia Y.

doi:10.1109/tpds.2021.3064345

Cited by 10 publications

(4 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) The principle of Purpose Limitation In this article, the FL server exposes the specific purpose of its model training to the client, who decides whether or not to participate in the training. At the same time, because the transmitted model is protected by differential privacy technology [31], the FL service provider cannot infer information from the model beyond the training task and, therefore, cannot use it for other purposes.…”

Section: Privacy Analysismentioning

confidence: 99%

FedHGCDroid: An Adaptive Multi-Dimensional Federated Learning for Privacy-Preserving Android Malware Classification

Jiang

Yin

Xia

et al. 2022

Entropy

View full text Add to dashboard Cite

With the popularity of Android and its open source, the Android platform has become an attractive target for hackers, and the detection and classification of malware has become a research hotspot. Existing malware classification methods rely on complex manual operation or large-volume high-quality training data. However, malware data collected by security providers contains user privacy information, such as user identity and behavior habit information. The increasing concern for user privacy poses a challenge to the current malware classification scheme. Based on this problem, we propose a new android malware classification scheme based on Federated learning, named FedHGCDroid, which classifies malware on Android clients in a privacy-protected manner. Firstly, we use a convolutional neural network and graph neural network to design a novel multi-dimensional malware classification model HGCDroid, which can effectively extract malicious behavior features to classify the malware accurately. Secondly, we introduce an FL framework to enable distributed Android clients to collaboratively train a comprehensive Android malware classification model in a privacy-preserving way. Finally, to adapt to the non-IID distribution of malware on Android clients, we propose a contribution degree-based adaptive classifier training mechanism FedAdapt to improve the adaptability of the malware classifier based on Federated learning. Comprehensive experimental studies on the Androzoo dataset (under different non-IID data settings) show that the FedHGCDroid achieves more adaptability and higher accuracy than the other state-of-the-art methods.

show abstract

Section: Privacy Analysismentioning

confidence: 99%

FedHGCDroid: An Adaptive Multi-Dimensional Federated Learning for Privacy-Preserving Android Malware Classification

Jiang

Yin

Xia

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

“…Differential privacy [13]- [15] has been widely used as a mainstream data perturbation mechanism for privacypreserving deep learning. Shokri and Shmatikov [6] proposed a distributed deep learning scheme with participant privacy in mind.…”

Section: Related Workmentioning

confidence: 99%

Cryptanalysis and Improvement of DeepPAR: Privacy-Preserving and Asynchronous Deep Learning for Industrial IoT

Chen

He²,

Wang

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Some works [122], [153]- [155], [158], [161], [163]- [167] applied the DP techniques from the standalone mode to the distributed systems to preserve the privacy of the training data for each agent. For example, Shokri et al [158] proposed a privacy-preserving distributed learning algorithm by adding Laplacian noise to each agent's gradients to prevent indirect leakage.…”

Section: A Differentially Private Collaborative Learningmentioning

confidence: 99%

“…Shokri et al [158] and Wei et al [159] composed the additive noise mechanisms using the strong composition theorem [152], leading to a linear increase in the privacy budget. In order to reduce aggregated noise in local updates, Han et al [163]dynamically adjust batch size and noise level according to the rate of critical input data and the sensitivity estimation.…”

Section: A Differentially Private Collaborative Learningmentioning

confidence: 99%

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Guo¹,

Zhang²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rapid demand of data and computational resources in deep learning systems, a growing number of algorithms to utilize collaborative machine learning techniques, for example, federated learning, to train a shared deep model across multiple participants. It could effectively take advantage of resource of each participant and obtain a more powerful learning system. However, integrity and privacy threats in such systems have greatly obstructed the applications of collaborative learning. And a large amount of works have been proposed to maintain the model integrity and mitigate the privacy leakage of training data during the training phase for different collaborate learning systems. Compared with existing surveys that mainly focus on one specific collaborate learning system, this survey aims to provide a systematic and comprehensive review of security and privacy researches in collaborative learning. Our survey first provides the system overview of collaborative learning, followed by an brief introduction of integrity and privacy threats. In an organized way, we then detail the existing integrity and privacy attacks as well as their defenses. We also list some open problems in this area and opensource the related papers on GitHub: https://github.com/csl-cqu/awesome-secure-collebrativelearning-papers.

show abstract

Accurate Differentially Private Deep Learning on the Edge

Cited by 10 publications

References 64 publications

FedHGCDroid: An Adaptive Multi-Dimensional Federated Learning for Privacy-Preserving Android Malware Classification

FedHGCDroid: An Adaptive Multi-Dimensional Federated Learning for Privacy-Preserving Android Malware Classification

Cryptanalysis and Improvement of DeepPAR: Privacy-Preserving and Asynchronous Deep Learning for Industrial IoT

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Contact Info

Product

Resources

About