UMBC Computer Science and Electrical Engineering Department
Browse by
The Computer Science and Electrical Engineering Department aims to maintain a program of excellence in teaching, research, and service for all of its programs. At the undergraduate level, we will provide students with a firm foundation of both the theory and practice of Computer Science and Computer Engineering. Our curricula also give students the social, ethical, and liberal education needed to make significant contributions to society. Students receiving a bachelor’s degree are ready to enter the work force as productive computer scientists or computer engineers, or to continue their education at the graduate or professional level.
At the graduate level, we are committed to developing the research and professional capabilities of students in Computer Science, Computer Engineering, Electrical Engineering and Cybersecurity. Our programs provide a deeper mastery of the basics of these fields, as well as opportunities to collaborate on leading-edge research with our faculty. Our faculty are engaged in both practical and theoretical research, often in partnership with government agencies, private industry and non-governmental organizations. The aim of this research is to advance knowledge within our disciplines and also to contribute to solving problems faced by our society.
Recent Submissions
-
Determining optical constants of 2D materials with neural networks from multi-angle reflectometry data
(IOP Publishing, 2020-02-25)Synthetically generated multi-angle reflectometry data is used to train a neural network based learning system to estimate the refractive index of atomically thin layered materials in the visible part of the electromagnetic ... -
Hidden Trigger Backdoor Attacks
(2019-12-21)With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial ... -
Fooling Network Interpretation in Image Classification
(2019-09-24)Deep neural networks have been shown to be fooled rather easily using adversarial attack algorithms. Practical methods such as adversarial patches have been shown to be extremely effective in causing misclassification. ... -
Would a File by Any Other Name Seem as Malicious?
(2019-10-10)Successful malware attacks on information technology systems can cause millions of dollars in damage, the exposure of sensitive and private information, and the irreversible destruction of data. Anti-virus systems that ... -
The Universal Decompositional Semantics Dataset and Decomp Toolkit
(2019-09-30)We present the Universal Decompositional Semantics (UDS) dataset (v1.0), which is bundled with the Decomp toolkit (v0.1). UDS1.0 unifies five high-quality, decompositional semantics-aligned annotation sets within a single ... -
LASCA: Learning Assisted Side Channel Delay Analysis for Hardware Trojan Detection
(2020-01-17)In this paper, we introduce a Learning Assisted Side Channel delay Analysis (LASCA) methodology for Hardware Trojan detection. Our proposed solution, unlike the prior art, does not require a Golden IC. Instead, it trains ... -
Adversarial Patches Exploiting Contextual Reasoning in Object Detection
(2019-12-21)The utilization of spatial context to improve accuracy in most fast object detection algorithms is well known. The detectors increase inference speed by doing a single forward pass per image which means they implicitly use ... -
A simple baseline for domain adaptation using rotation prediction
(2019-12-26)Recently, domain adaptation has become a hot research area with lots of applications. The goal is to adapt a model trained in one domain to another domain with scarce annotated data. We propose a simple yet effective method ... -
A New Burrows Wheeler Transform Markov Distance
(2019-12-30)Prior work inspired by compression algorithms has described how the Burrows Wheeler Transform can be used to create a distance measure for bioinformatics problems. We describe issues with this approach that were not widely ... -
Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks
(2020-01-16)In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational ... -
A Hybrid Quantum enabled RBM Advantage: Convolutional Autoencoders For Quantum Image Compression and Generative Learning
(2020-01-31)Understanding how the D-Wave quantum computer could be used for machine learning problems is of growing interest. Our work, in particular, evaluates the feasibility of using the D-Wave as a sampler for machine learning. ... -
3D Path-Following using MRAC on a Millimeter-Scale Spiral-Type Magnetic Robot
(IEEE, 2020-01-24)This paper focuses on the 3D path-following of a spiral-type helical magnetic swimmer in a water-filled workspace. The swimmer has a diameter of 2.5 mm, a length of 6 mm, and is controlled by an external time-varying ... -
High-Frequency Noise Peaks in Mo/Au Superconducting Transition-Edge Sensor Microcalorimeters
(Springer, 2020-01-13)The measured noise in Mo/Au transition-edge sensor (TES) microcalorimeters produced at NASA has recently been shown to be well described by a two-body electrothermal model with a finite thermal conductance between the X-ray ... -
Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints
Reinforcement learning (RL) has shown success in solving complex sequential decision making tasks when a well defined reward function is available. For agents acting in the real world, these reward functions need to be ... -
GrammarViz 2.0: A Tool for Grammar-Based Pattern Discovery in Time Series
The problem of frequent and anomalous patterns discovery in time series has received a lot of attention in the past decade. Addressing the common limitation of existing techniques, which require a pattern length to be known ... -
Understanding and Supporting Individuals Experiencing Severely Constraining Situational Impairments
(Springer Berlin Heidelberg, 2019-12-04)A special strain of situational impairment, termed “Severely Constraining Situational Impairments” (SCSI), was explored from a novel qualitative perspective. When a severely impairing event presents, the multitude and ... -
Reinforcement Quantum Annealing: A Quantum-Assisted Learning Automata Approach
(2020-01-01)We introduce the reinforcement quantum annealing (RQA) scheme in which an intelligent agent interacts with a quantum annealer that plays the stochastic environment role of learning automata and tries to iteratively find ... -
Quantum-Assisted Greedy Algorithms
(2019-12-08)We show how to leverage quantum annealers to better select candidates in greedy algorithms. Unlike conventional greedy algorithms that employ problem-specific heuristics for making locally optimal choices at each stage, ... -
Formation of optical supramolecular structures in a fibre laser by tailoring long-range soliton interactions
(Nature, 2019-12-17)Self-assembly of fundamental elements through weak, long-range interactions plays a central role in both supramolecular DNA assembly and bottom-up synthesis of nanostructures. Optical solitons, analogous in many ways to ... -
Scalability Analysis of Blockchain on a Serverless Cloud
(IEEE, 2019-12-10)While adopting Blockchain technologies to automate their enterprise functionality, organizations are recognizing the challenges of scalability and manual configuration that the state of art present. Scalability of Hyperledger ...
RSS 1.0