Confidential machine learning on untrusted platforms: a survey

Sharma, Sanjay; Chen, Keke

doi:10.1186/s42400-021-00092-8

Cited by 8 publications

(3 citation statements)

References 84 publications

(141 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike ours, the focus is on generic learning models and does not provide an in-depth analysis of neural network models. On a related study, Sagar and Keke [13] classify confidential learning techniques based on crypto-graphic primitives and hardware-based protocols. However, the authors' study is limited to SGX-based TEEs only.…”

Section: Related Surveysmentioning

confidence: 99%

“…Researchers proposed various techniques to adapt existing TEE technology for executing resource-heavy learning models inside resource-constrained TEEs. While there has been some work understanding solutions in protecting the confidentiality of the learning models and data during computation [10], [11], [12], [13], [14], there exists no prior work that systematically summarizes trusted neural network 1 execution. In this survey, we provide an in-depth review of existing trustworthy neural network execution techniques that use off-the-shelf TEEs (viz., SGX and TrustZone).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Trusted Deep Neural Execution—A Survey

Babar

Hasan

2023

IEEE Access

View full text Add to dashboard Cite

The growing use of deep neural networks (DNNs) in various applications has raised concerns about the security and privacy of model parameters and runtime execution. To address these concerns, researchers have proposed using trusted execution environments (TEEs) to build trustworthy neural network execution. This paper comprehensively surveys the literature on trusted neural networks, viz., answering how to efficiently execute neural models inside trusted enclaves. We review the various TEE architectures and techniques employed to achieve secure neural network execution and provide a classification of existing work. Additionally, we discuss the challenges and present a few open issues. We intend that this review will assist researchers and practitioners in understanding the state-of-the-art and identifying research problems.

show abstract

Section: Related Surveysmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Trusted Deep Neural Execution—A Survey

Babar

Hasan

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In recent years, the concept of cloud computing has emerged as one of the most important computing paradigms. Cloud computing has revolutionized information technology and access to processing and computing resources [1,2]. With cloud computing, individuals and organizations can access a shared network of managed and scalable IT resources such as servers, storage, and applications on-demand [3].…”

Section: Introductionmentioning

confidence: 99%

Practical autoencoder based anomaly detection by using vector reconstruction error

2023

View full text Add to dashboard Cite

Nowadays, cloud computing provides easy access to a set of variable and configurable computing resources based on user demand through the network. Cloud computing services are available through common internet protocols and network standards. In addition to the unique benefits of cloud computing, insecure communication and attacks on cloud networks cannot be ignored. There are several techniques for dealing with network attacks. To this end, network anomaly detection systems are widely used as an effective countermeasure against network anomalies. The anomaly-based approach generally learns normal traffic patterns in various ways and identifies patterns of anomalies. Network anomaly detection systems have gained much attention in intelligently monitoring network traffic using machine learning methods. This paper presents an efficient model based on autoencoders for anomaly detection in cloud computing networks. The autoencoder learns a basic representation of the normal data and its reconstruction with minimum error. Therefore, the reconstruction error is used as an anomaly or classification metric. In addition, to detecting anomaly data from normal data, the classification of anomaly types has also been investigated. We have proposed a new approach by examining an autoencoder’s anomaly detection method based on data reconstruction error. Unlike the existing autoencoder-based anomaly detection techniques that consider the reconstruction error of all input features as a single value, we assume that the reconstruction error is a vector. This enables our model to use the reconstruction error of every input feature as an anomaly or classification metric. We further propose a multi-class classification structure to classify the anomalies. We use the CIDDS-001 dataset as a commonly accepted dataset in the literature. Our evaluations show that the performance of the proposed method has improved considerably compared to the existing ones in terms of accuracy, recall, false-positive rate, and F1-score metrics.

show abstract

How Much Are Our Customers Worth? Investigating the Ease of Use and Usefulness of Data Coopetition for SME

Kaya,

Stallone

2023

Smart Innovation, Systems and Technologies

View full text Add to dashboard Cite

Confidential machine learning on untrusted platforms: a survey

Cited by 8 publications

References 84 publications

Trusted Deep Neural Execution—A Survey

Trusted Deep Neural Execution—A Survey

Practical autoencoder based anomaly detection by using vector reconstruction error

How Much Are Our Customers Worth? Investigating the Ease of Use and Usefulness of Data Coopetition for SME

Contact Info

Product

Resources

About