Challenges of Privacy-Preserving Machine Learning in IoT

Zheng, Mengyao; Xu, Dixing; Jiang, Linshan; Gu, Chaojie; Tan, Rui; Cheng, Peng

doi:10.1145/3363347.3363357

Cited by 23 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang19 [58] is a secure clustering method for preserving data privacy in cloud computing. The method combines a probabilistic C-Means algorithm [80] with a BGV encryption scheme [12] to produce HE-based big data clustering on a cloud environment. The main reason for choosing BGV in this scheme is its ability to ensure a correct result on the computation of encrypted data.…”

Section: ) Year 2019mentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving Deep Learning on Machine Learning as a Service—a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

The exponential growth of big data and deep learning has increased the data exchange traffic in society. Machine Learning as a Service, (MLaaS) which leverages deep learning techniques for predictive analytics to enhance decision-making, has become a hot commodity. However, the adoption of MLaaS introduces data privacy challenges for data owners and security challenges for deep learning model owners. Data owners are concerned about the safety and privacy of their data on MLaaS platforms, while MLaaS platform owners worry that their models could be stolen by adversaries who pose as clients. Consequently, Privacy-Preserving Deep Learning (PPDL) arises as a possible solution to this problem. Recently, several papers about PPDL for MLaaS have been published. However, to the best of our knowledge, no previous paper has summarized the existing literature on PPDL and its specific applicability to the MLaaS environment. In this paper, we present a comprehensive survey of privacypreserving techniques, starting from classical privacy-preserving techniques to well-known deep learning techniques. Additionally, we present a detailed description of PPDL and address the issue of using PPDL for MLaaS. Furthermore, we undertake detailed comparisons between state-of-the-art PPDL methods. Subsequently, we classify an adversarial model on PPDL by highlighting possible PPDL attacks and their potential solutions. Ultimately, our paper serves as a single point of reference for detailed knowledge on PPDL and its applicability to MLaaS environments for both new and experienced researchers.

show abstract

Section: ) Year 2019mentioning

confidence: 99%

“…• Zhen et al [12] focused on the challenges of privacypreserving machine learning in IoT. • Riazi et al [13] discussed deep learning in private data.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving Deep Learning on Machine Learning as a Service—a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Services with AI e privacy protection methods in ML can be generally divided into two kinds, namely, training schemes and inference schemes in [54].…”

Section: Privacy Preservation For Edge-enabled Iotmentioning

confidence: 99%

“…e privacy-preserving inference schemes focus on protecting the privacy data in the inference phase. Usually, in preserving inference schemes, a well-trained model receives the unclassified data sent by the EN for inference [54]. e common encryption methods include anonymization, cryptographic method, data obfuscation, and so on.…”

Section: Privacy Preservation For Edge-enabled Iotmentioning

confidence: 99%

Artificial Intelligence for Securing IoT Services in Edge Computing: A Survey

Liu

Huang

et al. 2020

Security and Communication Networks

View full text Add to dashboard Cite

With the explosive growth of data generated by the Internet of Things (IoT) devices, the traditional cloud computing model by transferring all data to the cloud for processing has gradually failed to meet the real-time requirement of IoT services due to high network latency. Edge computing (EC) as a new computing paradigm shifts the data processing from the cloud to the edge nodes (ENs), greatly improving the Quality of Service (QoS) for those IoT applications with low-latency requirements. However, compared to other endpoint devices such as smartphones or computers, distributed ENs are more vulnerable to attacks for restricted computing resources and storage. In the context that security and privacy preservation have become urgent issues for EC, great progress in artificial intelligence (AI) opens many possible windows to address the security challenges. The powerful learning ability of AI enables the system to identify malicious attacks more accurately and efficiently. Meanwhile, to a certain extent, transferring model parameters instead of raw data avoids privacy leakage. In this paper, a comprehensive survey of the contribution of AI to the IoT security in EC is presented. First, the research status and some basic definitions are introduced. Next, the IoT service framework with EC is discussed. The survey of privacy preservation and blockchain for edge-enabled IoT services with AI is then presented. In the end, the open issues and challenges on the application of AI in IoT services based on EC are discussed.

show abstract

“…Moreover, it introduce a privacy-preserving inference scheme where IoT objects are run in a neural network which is lightweight in nature thereby obfuscate the data prior to its transmission, next in the cloud a deep neural network is run thereby classifying the previously obfuscated data. Performance evaluation is done with MNIST dataset that yields satisfactory results [13].…”

Section: Related Workmentioning

confidence: 99%

A Novel Framework for Privacy-Preserving Using Data Aggregation in Internet of Things (Iot)

Mohapatra¹

2020

ijarcs

View full text Add to dashboard Cite

Today with the development of Internet of Things (IoT) technology its security and privacy becomes very much essential because this technology provide the facility for accessing the devices or resources from anywhere and anytime. For providing the security and privacy to IoT various technologies has been developed but in this we propose data aggregation mechanism in which it uses one-time pad and symmetric key to make our data secure and preserve the privacy of it. This mechanism takes less computation time, improve processing speed and also require less cost in implementation. The implementation of proposed approach is done in widely used Python technology which produces better results. In last the proposed mechanism provides more security and preserves our data.

show abstract

Challenges of Privacy-Preserving Machine Learning in IoT

Cited by 23 publications

References 38 publications

Privacy-Preserving Deep Learning on Machine Learning as a Service—a Comprehensive Survey

Privacy-Preserving Deep Learning on Machine Learning as a Service—a Comprehensive Survey

Artificial Intelligence for Securing IoT Services in Edge Computing: A Survey

A Novel Framework for Privacy-Preserving Using Data Aggregation in Internet of Things (Iot)

Contact Info

Product

Resources

About