Machine learning algorithms based on neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy sensitive. To address this issue, we develop new techniques to provide solutions for running deep neural networks over encrypted data. In this paper, we develop new techniques to adopt deep neural networks within the practical limitation of current homomorphic encryption schemes. We focus on training and classification of the well-known neural networks and convolutional neural networks. First, we design methods for approximation of the activation functions commonly used in CNNs (i.e. ReLU, Sigmoid, and Tanh) with low degree polynomials which is essential for efficient homomorphic encryption schemes. Then, we train neural networks with the approximation polynomials instead of original activation functions and analyze the performance of the models. Finally, we implement neural networks and convolutional neural networks over encrypted data and measure performance of the models.

No description available.

No description available.

AbstractThe mapping of habitats is the first step that is done in policies that target theenvironment, as well as in spatial planning and management. The biodiversityplans are always centered around habitats. Therefore, constant monitoring ofthese delicate species in terms of health, changes, and extinction is a must inbiodiversity plans. Human activities are constantly growing, resulting in theextinction of land and marine habitats. Land habitats are being destroyed using airpollution and the cutting of forests. At the same time, marine habitats are beingdestroyed due to acidification of ocean waters and waste materials from theindustries and pollution. The author has focused on aquatic habitats in thisdissertation, mainly coral reefs. An estimate of 27% of coral reef ecosystems havebeen destroyed, and a further 30% are at risk of being damaged in the comingyears. Coral reefs occupy 1% of the ocean floor, and yet they provide a home to30% of marine organisms. To analyze the health of these aquatic habitats, theyneed to be assessed through habitat mapping. Habitat mapping shows thegeographic distribution of different habitats within a particular area. Marinehabitats are typically mapped using camera imagery. The quality of underwaterimages suffers from the characteristics of the marine environment. This results inblurry images or containing particles that cover many parts of an image. Toovercome this, underwater image enhancement algorithms are used to preprocessimages beforehand. Now, there are many underwater image enhancementalgorithms that target different characteristics of the marine environment, butthere is no consensus among researchers about a single underwater technique thatcan be used for any marine dataset. In this dissertation, multiple experiments onvarious popular image enhancement techniques (seven) were conducted and usedto reach a decision about a single underwater approach for all datasets. Thedatasets include EILAT, EILAT2, RSMAS, and MLC08. Also, two state-of-the-artdeep convolutional neural networks for habitat mapping, i.e., DenseNet andMobileNet tested. Maximum results from the combination of Contrast LimitedAdaptive Histogram Equalization (CLAHE) achieved as underwater imageenhancement technique and DenseNet as deep convolutional network. / Not applicable

By organically fusing the methods of convolutional neural network (CNN) and recurrent neural network (RNN), this dissertation focuses on the application of optical character recognition and image classification processing. The first part of this dissertation presents an end-to-end novel receipt recognition system for capturing effective information from receipts (CEIR). The main contributions of this research part are divided into three parts. First, this research develops a preprocessing method for receipt images. Second, the modified connectionist text proposal network is introduced to execute text detection. Third, the CEIR combines the convolutional recurrent neural network with the connectionist temporal classification with maximum entropy regularization as a loss function to update the weights in networks and extract the characters from receipt. The CEIR system is validated with the scanned receipts optical character recognition and information extraction (SROIE) database. Furthermore, the CEIR system has strong robustness and can be extended to a variety of different scenarios beyond receipts. For the convolutional recurrent structure application of land use image classification, this dissertation comes up with a novel deep learning model for land use classification, the convolutional recurrent land use classifier (CRLUC), which further improves the accuracy in classifying remote sensing land use images. Besides, the convolutional fully-connected neural networks with hard sample memory pool structure (CFMP) is invented to tackle the remote sensing land use image classification tasks. The CRLUC and CFMP algorithm performances are tested in popular datasets. Experimental studies show the proposed algorithms can classify images with higher accuracy and fewer training episodes compared to popular image classification algorithms.

Automation is fundamentally changing many industries and retail is no exception. Moonshopis a South African venture trying to solve the problem of autonomous grocery storesusing cameras and computer vision. This project is the continuation of a hackathon heldto explore different methods for Human Action Recognition in Moonshop’s stores.Throughout the project a pipeline for data processing has been developed and two typesof Graph-Convolutional Networks, CTR-GCN and ST-GCN, have been implementedand evaluated on the data produced by this pipeline. The resulting scores aren’t goodenough to call it a success. However, this is not necessarily a fault of the models. Rather,there wasn’t enough data to train on and the existing data was of varying to low quality.This makes it complicated to justly judge the models’ performances. In the future, moreresources should be spent on generating more and better data in order to really evaluatethe feasibility of using Human Action Recognition and Graph-Convolutional Networksat Moonshop.

Side-channel attacks avoid complex analysis of cryptographic algorithms, instead they use side-channel signals captured from a software or a hardware implementation of the algorithm to recover its secret key. Recently, deep learning models, especially Convolutional Neural Networks (CNN), have been shown successful in assisting side-channel analysis. The attacker first trains a CNN model on a large set of power traces captured from a device with a known key. The trained model is then used to recover the unknown key from a few power traces captured from a victim device. However, previous work had three important limitations: (1) little attention is paid to the effects of training and testing on traces captured from different devices; (2) the effect of different power models on the attack’s efficiency has not been thoroughly evaluated; (3) it is believed that, in order to recover all bytes of a key, the CNN model must be trained as many times as the number of bytes in the key.This thesis aims to address these limitations. First, we show that it is easy to overestimate the attack’s efficiency if the CNN model is trained and tested on the same device. Second, we evaluate the effect of two common power models, identity and Hamming weight, on CNN-based side-channel attack’s efficiency. The results show that the identity power model is more effective under the same training conditions. Finally, we show that it is possible to recover all key bytes using the CNN model trained only once. / Sidokanalattacker undviker komplex analys av kryptografiska algoritmer, utan använder sig av sidokanalssignaler som tagits från en mjukvara eller en hårdvaruimplementering av algoritmen för att återställa sin hemliga nyckel. Nyligen har djupa inlärningsmodeller, särskilt konvolutionella neurala nätverk (CNN), visats framgångsrika för att bistå sidokanalanalys. Anfallaren tränar först en CNN-modell på en stor uppsättning strömspår som tagits från en enhet med en känd nyckel. Den utbildade modellen används sedan för att återställa den okända nyckeln från några kraftspår som fångats från en offeranordning. Tidigare arbete hade dock tre viktiga begränsningar: (1) Liten uppmärksamhet ägnas åt effekterna av träning och testning på spår som fångats från olika enheter; (2) Effekten av olika kraftmodeller på attackerens effektivitet har inte utvärderats noggrant. (3) man tror att CNN-modellen måste utbildas så många gånger som antalet byte i nyckeln för att återställa alla bitgrupper av en nyckel.Denna avhandling syftar till att hantera dessa begränsningar. Först visar vi att det är lätt att överskatta attackens effektivitet om CNN-modellen är utbildad och testad på samma enhet. För det andra utvärderar vi effekten av två gemensamma kraftmodeller, identitet och Hamming-vikt, på CNN-baserad sidokanalangrepps effektivitet. Resultaten visar att identitetsmaktmodellen är effektivare under samma träningsförhållanden. Slutligen visar vi att det är möjligt att återställa alla nyckelbyte med hjälp av CNN-modellen som utbildats en gång.

Printed circuit boards used in most ordinary electrical devices are usually equipped through an assembly line. Pick and place machines as part of those lines require accurate detection of incorrectly picked components, and this is commonly performed via image analysis. The goal of this project is to investigate if we can achieve state-of-the-art performance in an industrial quality assurance task through the application of artificial neural networks. Experiments regarding different network architectures and data modifications are conducted to achieve precise image classification. Although the classification rates do not surpass or equal the rates of the existing vision-based detection system, there remains great potential in the deployment of a machine-learning-based algorithm into pick and place machines. / Tryckta kretskort som används i de flesta vanliga elektroniska produkter är vanligtvis monterade i monteringslinjer. Ytmonteringsmaskinerna i dessa monteringslinjer kräver exakt detektering av felaktigt plockade komponenter, vilket ofta genomförs med hjälp av bildanalys. Målet med detta projekt är att undersöka om vi kan uppnå framstående resultat i en industriell kvalitetssäkringsuppgift genom användandet av artificiella neuronnätverk. Experiment utförs med olika nätverksarkitekturer och datamodifikationer för att uppnå exakt bildklassificering.  Även om klassificeringsgraderna inte uppnår klassificeringsgraderna hos existerande synbaserade detekteringssystem, finns en stor potential för användandet av maskininlärningsbaserade algoritmer i ytmonteringsmaskiner.

In this report we evaluated how the complexity of a Convolutional Neural Network (CNN), in terms of number of filters, size of filters and dropout, affects the performance on the rating prediction accuracy in a tightly coupled hybrid recommender system. We also evaluated the effect on the rating prediction accuracy for pretrained CNNs in comparison to non-pretrained CNNs. We found that a less complex model, i.e. smaller filters and less number of filters, showed trends of better performance. Less regularization, in terms of dropout, had trends of better performance for the less complex models. Regarding the comparison of the pretrained models and non-pretrained models the experimental results were almost identical for the two denser datasets while pretraining had slightly worse performance on the sparsest dataset. / I denna rapport utvärderade vi komplexiteten på ett neuralt faltningsnätverk (eng. Convolutional Neural Network) i form av antal filter, storleken på filtren och regularisering, i form av avhopp (eng. dropout), för att se hur dessa hyperparametrar påverkade träffsäkerheten för rekommendationer i ett hybridrekommendationssystem. Vi utvärderade även hur förträning av det neurala faltningsnätverket påverkade träffsäkerheten för rekommendationer i jämförelse med ett icke förtränat neuralt faltningsnätverk. Resultaten visade trender på att en mindre komplex modell, det vill säga mindre och färre filter, gav bättre resultat. Även mindre regularisering, i form av avhopp, gav bättre resultat för mindre komplexa modeller. Gällande jämförelsen med förtränade modeller och icke förtränade modeller visade de experimentella resultaten nästan ingen skillnad för de två kompaktare dataseten medan förträning gav lite sämre resultat på det glesaste datasetet.

In this thesis we present two approaches to improve automatic playtesting using player modeling. By modeling various cohorts of players we are able to train Convolutional Neural Network based agents that simulate human gameplay using different strategies directly learnt from real player data. The goal is to use the developed agents to predict useful metrics of newly created game content. We validated our approaches using the game Candy Crush Saga, a non-deterministic match-three puzzle game with a huge search space and more than three thousand levels available. To the best of our knowledge this is the first time that player modeling is applied in a match-three puzzle game. Nevertheless, the presented approaches are general and can be extended to other games as well. The proposed methods are compared to a baseline approach that simulates gameplay using a single strategy learnt from random gameplay data. Results show that by simulating different strategies, our approaches can more accurately predict the level difficulty, measured as the players’ success rate, on new levels. Both the approaches improved the mean absolute error by 13% and the mean squared error by approximately 23% when predicting with linear regression models. Furthermore, the proposed approaches can provide useful insights to better understand the players and the game. / I denna uppsats presenterar vi två tillvägagångssätt för att förbättra automatisk speltestning genom modellering av spelare. Genom att modellera olika grupper av spelare kunde vi träna Convolutional Neural Network-baserade agenter för att simulera mänskligt spelande med hjälp av olika strategier som är lärda direkt från mänsklig spelardata. Målet är att använda de utvecklade agenterna för att förutsäga användbar metrik av nyskapat spelinnehåll. Vi validerade vårt tillvägagångssätt genom Candy Crush Saga, ett icke-deterministiskt 3-matchnings pusselspel med mer än tre tusen nivåer. Detta är första gången som spelarmodellering appliceras på ett 3-matchnings pusselspel. De presenterade tillvägagångssätten är mer generella och kan utökas till andra spel. De föreslagna tillvägagångssätten är jämförda med ett tillvägagångssätt som simulerar spelande genom en strategi som är lärd direkt från slumpmässig mänsklig spelardata. Resultatet visar att vårt tillvägagångssätt, genom simulering av olika strategier är, mer exakt för att förutsäga spelarens svårighet, mätt genom spelarens framgång, på nya nivåer. Båda tillvägagångssätten förbättrade mean absolute error med 13% och mean squared error med ungefär 23%. Dessutom kan de föreslagna tillvägagångssätten ge en användbar insikt för att bättre förstå spelarna och spelet.