ACM Tech Talk Series

​A Practitioner’s Introduction to Deep Learning

​Ashwin Kumar Ganesan, PhD student

1:00-2:00pm Friday, 17 November 2017​, ITE325, UMBC

In recent years, Deep Neural Networks have been highly successful at performing a number of tasks in computer vision, natural language processing and artificial intelligence in general. The remarkable performance gains have led to universities and industries investing heavily in this space. This investment creates a thriving open source ecosystem of tools & libraries that aid the design of new architectures, algorithm research as well as data collection.

This talk (and hands-on session) introduce people to some of the basics of machine learning, neural networks and discusses some of the popular neural network architectures. We take a dive into one of the popular libraries, Tensorflow, and an associated abstraction library Keras.

To participate in the hands-on aspects of the workshop, bring a laptop computer with Python installed and install the following libraries using pip.  For windows or (any other OS) consider doing an installation of anaconda that has all the necessary libraries.

• numpy, scipy & scikit-learn
• tensorflow / tensoflow-gpu (The first one is the GPU version)
• matplotlib for visualizations (if necessary)
• jupyter & ipython (We will use python2.7 in our experiments)

Following are helpful links:

• https://www.tensorflow.org/install/
• https://www.scipy.org/install.html

Contact Nisha Pillai (NPillai1 at umbc.edu) with any questions regarding this event.

Open House: UMBC Graduate Professional Programs

The Fall Open House for UMBC Professional Programs, including the graduate programs on Cybersecurity and Data Science, takes place this coming Wednesday evening, 25 October 2017, at BWTECH South (map) from 6:00-7:30pm.

Students interested in pursuing such programs (MPS degrees and/or certificates) or just to learn more about the field are encouraged to register and attend. Current students interested in pursuing a BS/MPS option for selected programs (such as Cybersecurity or Data Science) are especially welcome.

Attendees who apply to start in Spring 18 will have their UMBC application fee waived.

The programs represented include:

• Cybersecurity
• Data Science
• Engineering Management
• Systems Engineering
• Health Information Technology
• Instructional Systems Development

Program directors for these programs will present in individual breakout sessions and relevant support staff from DPS, the UMBC Graduate School, Veterans Affairs, etc. will be on-hand to provide administrative overviews, answer questions, and mingle. Refreshments will be provided.

for more information, directions and to register, see here.

The upcoming CRA-Women Graduate Student Cohort for Women will be held April 13-14, 2018 in San Francisco, CA. CRA-W Grad Cohort for Women is a two-day workshop for female students in their first, second, or third year of graduate school in computing fields. The application is available here and closes November 30.

The workshop is generously funded by sponsors from industry, academia, the National Science Foundation, and the computing community. The workshop aims to increase the ranks of senior women in computing-related studies and research by building and mentoring nationwide communities of women through their graduate studies.

HackUMBC was a 24-hour tech innovation marathon where students across the East Coast collaborate on new ideas to build mobile, web and hardware projects. HackUMBC involved a diverse group of students, undergraduate, graduate and high school students over 18, who enjoy a weekend of hacking, workshops, tech talks, networking, and other fun activities. At the end of 24 hours, projects wer presented and judged for different prize categories from sponsors and other organizations. The winners were:

• First place: Kokua. Bringing communities together around natural disaster aid
• Second place: Cellular Rover. An advanced RC rover with unlimited radio range
• Third place: Identification of Most Harmed Regions in Puerto Rico. Using satellite and other data to map out the areas of Puerto Rico that were the most impaired due to Hurricane Maria
• Best Hardware Hack: Rap-Me-A-Recipe

• Best Design Hack: Eclipse Blazer. It’s a programmable RGB LED jacket that can really make you stand out in any crowd
• Best Unique Hack: Morsr. We set the foundation circuitry and code for a new form of audio, visual and physical communication: the TeleGraph

Want to learn about blockchain or machine learning? Like to get hands-on experience building software for IoT? Participate in DevFestMD ’17 and do all of that and more! DevFestMD is a day-long tech event filled with talks and hands-on workshops. So whether you’re thinking about joining the tech community or a seasoned software engineer, they have something for you. Early Bird tickets are only $10 and includes breakfast and lunch.

DevFestMD takes place on Friday, October 27, at Betamore at City Garage, 101 West Dickman St., Baltimore

HackUMBC hackathon, Saturday-Sunday 7-8 October 2017

HackUMBC is a 24-hour tech innovation marathon where students across the East Coast collaborate on new ideas to build mobile, web and hardware projects. HackUMBC invites diverse groups of students, undergraduate, graduate and high school students over 18, to enjoy a weekend of hacking, workshops, tech talks, networking, and other fun activities. At the end of 24 hours, projects are presented and judged for different prize categories from sponsors and other organizations.

What if I don’t have a team or an idea?: No problem! You can find a team once you arrive. Most hackers arrive without a team. You will often find inspiration for ideas at the hackathon.

What if I don’t code?: This is the perfect opportunity to learn something new! There will be workshops geared towards beginners and mentors to help you throughout the event.

What can I build?: Anything! Web, mobile, desktop, and hardware projects are all welcome. Projects will be judged based on creativity, technical difficulty, polish, and usefulness.

Will there be hardware? HackUMBC has partnered with MLH to provide hardware hacking resources to all hackers. Check out the full list of hardware.

How much does it cost? HackUMBC is free! Food, beverages, swag, workspaces, and sleeping areas will be provided. You just have to travel to the event and we will take care of the rest!

The event starts in Meyerhoff 030 at 10:00am on Saturday, October 7 and ends at 3:30pm on Sunday, October 8. Visit the HackUMBC site for complete details and to register.

UMBC Cyber Defense Lab

Results from the SFS Summer Research Study at UMBC

Enis Golaszewski, UMBC

12:00–1:00pm, Friday, 8 September 2017
ITE 228 (or nearby), UMBC

In summer 2017, UMBC held a cybersecurity research workshop that featured the UMBC Scholarship For Service (SFS) cohort working with the cooperation of the UMBC Department of Information Technology (DoIT) to analyze the security of NetAdmin, a software tool developed and used by DoIT. The workshop included six new SFS scholars transferring to UMBC from Montgomery College and Prince George’s Community College and provided students with experience in analyzing the security of software while uncovering serious flaws in the NetAdmin tool. NetAdmin allows authorized research faculty at UMBC to make research servers running on campus accessible to connections originating from off-campus.

Because NetAdmin directly modifies the campus firewall, possible security weaknesses in its architecture, implementation, or usage could present a significant risk to UMBC computer systems. During the four-day study, students uncovered multiple critical security flaws and developed recommendations for mitigating them. These flaws include architectural weaknesses, injection attack vulnerabilities, and susceptibility to man-in-the-middle attacks. The workshop was successful for improving the security of NetAdmin as well as integrating the incoming SFS scholars with the existing UMBC cohort.

In this talk, we will focus on the technical details of our security analysis of the NetAdmin tool.

Enis Golaszewski is a PhD student and SFS scholar in computer science working with Dr. Sherman on protocol analysis and the security of software-defined networks. Email:

Host: Alan T. Sherman,

AI system designs clothing for your personal fashion style

Everyone knows that more and more data is being collected about our everyday activities, like where we go online and in the physical world. Much of that data is being used for personalization. Recent UMBC CSEE Masters student Prutha Date explored a novel kind of personalization – creating clothing that matches your personal style.

Date developed a system that takes as input pictures of clothing in your closet, extracts a digitial representation of your style preferences, and then applies that style to new articles of clothing, like a picture pair of pants or a dress you find online. This work meshes well with recent efforts by Amazon to manufacture clothing on demand. Imagine being able to click on an article of clothing available online, personalize it to your style, and then have it made and shipped right to your door!

This innovative research was cited in a recent article in MIT Technology Review, Amazon Has Developed an AI Fashion Designer.

Tim Oates, a professor at the University of Maryland in Baltimore County, presented details of a system for transferring a particular style from one garment to another. He suggests that this approach might be used to conjure up new items of clothing from scratch. “You could train [an algorithm] on your closet, and then you could say here’s a jacket or a pair of pants, and I’d like to adapt it to my style,” Oates says.

Fashion designers probably shouldn’t fret just yet, though. Oates and other point out that it may be a long time before a machine can invent a fashion trend. “People innovate in areas like music, fashion, and cinema,” he says. “What we haven’t seen is a genuinely new music or fashion style that was generated by a computer and really resonated with people.”

You can read more about the work in a recent paper by Prutha Date, Ashwinkumar Ganesan and Tim Oates, Fashioning with Networks: Neural Style Transfer to Design Clothes. The paper describes how convolutional neural networks were used to personalize and generate new custom clothes based on a person’s preference and by learning their fashion choices from a limited set of clothes from their closet.

Ph.D. Dissertation Defense

Context-dependent privacy and security management on mobile devices

Prajit Kumar Das

8:00-11:00am Tuesday, 22 August 2017, ITE325b, UMBC

There are ongoing security and privacy concerns regarding mobile platforms which are being used by a growing number of citizens. Security and privacy models typically used by mobile platforms use one-time permission acquisition mechanisms. However, modifying access rights after initial authorization in mobile systems is often too tedious and complicated for users. User studies show that a typical user does not understand permissions requested by applications or are too eager to use the applications to care to understand the permission implications. For example, the Brightest Flashlight application was reported to have logged precise locations and unique user identifiers, which have nothing to do with a flashlight application’s intended functionality, but more than 50 million users used a version of this application which would have forced them to allow this permission. Given the penetration of mobile devices into our lives, a fine-grained context-dependent security and privacy control approach needs to be created.

We have created Mithril as an end-to-end mobile access control framework that allows us to capture access control needs for specific users, by observing violations of known policies. The framework studies mobile application executables to better inform users of the risks associated with using certain applications. The policy capture process involves an iterative user feedback process that captures policy modifications required to mediate observed violations. Precision of policy is used to determine convergence of the policy capture process. Policy rules in the system are written using Semantic Web technologies and the Platys ontology to define a hierarchical notion of context. Policy rule antecedents are comprised of context elements derived using the Platys ontology employing a query engine, an inference mechanism and mobile sensors. We performed a user study that proves the feasibility of using our violation driven policy capture process to gather user-specific policy modifications.

We contribute to the static and dynamic study of mobile applications by defining “application behavior” as a possible way of understanding mobile applications and creating access control policies for them. Our user study also shows that unlike our behavior-based policy, a “deny by default” mechanism hampers usability of access control systems. We also show that inclusion of crowd-sourced policies leads to further reduction in user burden and need for engagement while capturing context-based access control policy. We enrich knowledge about mobile “application behavior” and expose this knowledge through the Mobipedia knowledge-base. We also extend context synthesis for semantic presence detection on mobile devices by combining Bluetooth, low energy beacons and Nearby Messaging services from Google.

Committee: Drs. Anupam Joshi (chair), Tim Finin (co-chair), Tim Oates, Nilanjan Banerjee, Arkady Zaslavsky, (CSIRO), Dipanjan Chakraborty (Shopperts)

Ph.D. Dissertation Defense

Identifying and Ordering Scalar Adjectives using Lexical Substitution

Bryan Wilkinson

1:00pm Friday, 18 August 2017, ITE 325b, UMBC

Lexical semantics provides many important resources in natural language processing, despite the recent preferences for distributional methods. In this dissertation we investigate an under-represented lexical relationship, that of scalarity. We define sclarity as it relates to adjectives and introduce novel methods to identify words belonging to a particular scale and to order those words once they are found. This information has important uses in both traditional linguistics as well as natural language processing. We focus on solving both these problems using lexical substitution, a technique that allows us to determine the best substitute word for a given word in a sentence. We also produce two new datasets: a gold standard of scalar adjectives for use in the development and evaluation of methods like the ones introduces here, and a test set of indirect question-answer pairs, one possible application of scalar adjectives.

Committee: Drs. Tim Oates, CSEE (Chair), Charles Nicholas, Tim Finin, Shimei Pan (IS) and Mona Diab (GWU CS)