A new algorithm for training sparse autoencoders

Shamsabadi, Ali Shahin; Babaie‐Zadeh, Massoud; Seyyedsalehi, Seyyede Zohreh; Rabiee, Hamid R.; Jutten, Christian

doi:10.23919/eusipco.2017.8081588

Cited by 11 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning the encoded representation can be achieved by restricting the number of nodes in the encoding layers as done in undercomplete autoencoders [42]. Overcomplete autoencoders learn structure by imposing other regularization constraints on the encoding layer such as sparsity as in sparse autoencoders [44], or addition of noise as in denoising autoencoders [45]. Convolutional autoencoders (CAE) exploit spatial relationships in data by weight sharing [46].…”

Section: Autoencodersmentioning

confidence: 99%

Device Authentication Codes based on RF Fingerprinting using Deep Learning

Bassey¹,

Li²,

Qian³

2021

ICST Transactions on Security and Safety

View full text Add to dashboard Cite

In this paper, we propose Device Authentication Code (DAC), a novel method for authenticating IoT devices with wireless interface, by exploiting their radio frequency (RF) signatures. The proposed DAC is based on RF fingerprinting, an information-theoretic method, feature learning, and the discriminatory power of deep learning. Specifically, an autoencoder is used to automatically extract features from the RF traces and the reconstruction error is used as the DAC, and this DAC is unique to each individual device. Then Kolmogorov-Smirnov (K-S) test is used to match the distribution of the reconstruction error generated by the receiver and the DAC in the received message, and the result will determine whether the device of interest is an intruder. We validate this concept on two experimentally collected RF traces from six ZigBee devices and five universal software defined radio peripheral devices, respectively. The traces span a range of Signal-to-Noise Ratio by varying locations, mobility of the devices, channel interference, and noise to ensure robustness of the model. Experimental results demonstrate that DAC is able to prevent device impersonation by extracting salient features that are unique to each wireless device of interest and can be used to identify radio frequency devices. Furthermore, the proposed method does not need the RF traces of the intruder during model training to be able to identify devices not seen during training, which makes it practical.

show abstract

Section: Autoencodersmentioning

confidence: 99%

Device Authentication Codes based on RF Fingerprinting using Deep Learning

Bassey¹,

Li²,

Qian³

2021

ICST Transactions on Security and Safety

View full text Add to dashboard Cite

show abstract

“…where w k is the kernel width, h k is the kernel height, and c p and c p+1 are the number of feature channels in the pth and (p + 1)-th convolutional layers. Each reconstructor R i (•) : R w×h×c → R w×h×c is instantiated with a T -layer deep convolutional autoencoder [68], [69] composed of a parametric encoder, followed by a parametric decoder…”

Section: Private Trainingmentioning

confidence: 99%

PrivEdge: From Local to Distributed Private Training and Prediction

Shamsabadi

Gascón

Haddadi

et al. 2020

IEEE Trans.Inform.Forensic Secur.

Self Cite

View full text Add to dashboard Cite

Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when dealing with sensitive personal data. To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service. With PrivEdge, each user independently uses their private data to locally train a one-class reconstructive adversarial network that succinctly represents their training data. As sending the model parameters to the service provider in the clear would reveal private information, PrivEdge secret-shares the parameters among two non-colluding MLaaS providers, to then provide cryptographically private prediction services through secure multi-party computation techniques. We quantify the benefits of PrivEdge and compare its performance with state-ofthe-art centralised architectures on three privacy-sensitive imagebased tasks: individual identification, writer identification, and handwritten letter recognition. Experimental results show that PrivEdge has high precision and recall in preserving privacy, as well as in distinguishing between private and non-private images. Moreover, we show the robustness of PrivEdge to image compression and biased training data.

show abstract

“…For each input in the encoder unit, a linear combination of input elements is mapped onto the hidden layer representation using a nonlinear function. 36 The input values are matched with the values of the hidden layer by using Equation 11 with the definitions below: 37 Similarly, in the decoder section, it attempts to recreate the input by applying a typical nonlinear function to a linear combination of the resulting representational elements.…”

Section: Figure 7 Particle Filter Flowchartmentioning

confidence: 99%

Performance analysis of machine learning and deep learning classification methods for indoor localization in Internet of things environment

Turgut

Üstebay

Aydın

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The ability to detect the mobile user's location with high precision in indoor networks is particularly difficult due to the environmental characteristics and high dynamics of the indoor networks. The use of different technologies in the system to be developed to determine the position with high accuracy is important for overcoming the disadvantage(s) of any technology. To design a high‐precision indoor positioning method, it is important create an Internet of things (IoT) environment which uses hybrid technologies. The proposed system has been tested on an IoT environment by using two phases: preproccessing and localization. The corresponding environment is an original IoT environment, which allows to collect a hybrid dataset consists of WiFi, Bluetooth Low Energy, and Earth's magnetic field values. HALICDB dataset is created in the related ecosystem. To make a comparison with HALICDB, RFKONDB is used to create RFKON_HIBRID with similar signal values. The signal values obtained from the datasets are first passed through a particle filter. In the localization phase, a reference signal map is obtained for the detection of the moving objects in the indoor areas that are in the IoT environment using the fingerprint method. In the offline phase, the different machine learning methods are used in fingerprint maps for classification. It is seen that the highest accuracy is received through stacked sparse autoencoder from the deep learning methods due to the overcomplete network structure offered by the IoT environment on both datasets.

show abstract

A new algorithm for training sparse autoencoders

Cited by 11 publications

References 20 publications

Device Authentication Codes based on RF Fingerprinting using Deep Learning

Device Authentication Codes based on RF Fingerprinting using Deep Learning

PrivEdge: From Local to Distributed Private Training and Prediction

Performance analysis of machine learning and deep learning classification methods for indoor localization in Internet of things environment

Contact Info

Product

Resources

About