Computer Engineering Commons^™

Enhanced Security Utilizing Side Channel Data Analysis, Michael Taylor

Computer Science and Engineering Theses and Dissertations

The physical state of a system is affected by the activities and processes in which it is tasked with carrying out. In the past there have been many instances where such physical changes have been exploited by bad actors in order to gain insight into the operational state and even the data being held on a system. This method of side channel exploitation is very often effective due to the relative difficulty of obfuscating activity on a physical level. However, in order to take advantage of side channel data streams one must have a detailed working knowledge of how a …

Using A Light-Based Power Source To Defeat Power Analysis Attacks, Remus Valentin Tumac

Computer Science and Engineering Theses and Dissertations

Power analysis attacks exploit the correlation between the information processed by an electronic system and the power consumption of the system. By powering an electronic system with an optical power source, we can prevent meaningful information from being leaked to the power pins and captured in power traces. The relatively constant current draw of the optical power source hides any variability in the power consumption of the target system caused by the logic gates' switching activity of the system as observed at the power pins. This thesis will provide evidence to show that using an optical power source should make …

Exploring Neural Networks For Predicting Sentinel-C Backscatter Between Image Acquisitions, Zhongdi Wu

Computer Science and Engineering Theses and Dissertations

Measuring moisture dynamics in soil and overlying vegetation is key to understanding ecosystem and agricultural dynamics in many contexts. For many applications, moisture information is demanded at high temporal frequency over large areas. Sentinel-1 C-band radar backscatter satellite images provide a repeating sequence of fine-resolution (10-m) observations that can be used to infer soil and vegetation moisture, but the 12-day interval between satellite observations is infrequent relative to the sensed moisture dynamics. Machine learning approaches have been used to predict soil moisture at higher spatial resolutions than the original satellite images, but little effort has been made to increase the …

Reducing Power During Manufacturing Test Using Different Architectures, Yi Sun

Computer Science and Engineering Theses and Dissertations

Power during manufacturing test can be several times higher than power consumption in functional mode. Excessive power during test can cause IR drop, over-heating, and early aging of the chips. In this dissertation, three different architectures have been introduced to reduce test power in general cases as well as in certain scenarios, including field test.

In the first architecture, scan chains are divided into several segments. Every segment needs a control bit to enable capture in a segment when new faults are detectable on that segment for that pattern. Otherwise, the segment should be disabled to reduce capture power. We …

Bert For Question Answering On Bioasq, Eric R. Fu, Rikel Djoko, Maysam Mansor, Robert Slater

SMU Data Science Review

Machine reading comprehension and question answering are topics of considerable focus in the field of Natural Language Processing (NLP). In recent years, language models like Bidirectional Encoder Representations from Transformers (BERT) [3] have been very successful in language related tasks like question answering. The difficulty of the question answering task lies in developing accurate representations of language and being able to produce answers for questions. In this study, the focus is to investigate how to train and fine tune a BERT model to improve its performance on BioASQ, a challenge on large scale biomedical question answering. Our most accurate BERT …