Department of Computer Science and Electrical Engineering
Talk: Role of the Defense Information Systems Agency, 12p Fri 9/22
UMBC Cyber Defense Lab
Tech Talk with the Defense Information Systems Agency (DISA)
Lead Engineer – Cyber Security Range
IDC – Cyber Workforce Development Division
Defense Information Systems Agency (DISA)
12:00–1:00pm, Friday, 22 September 2017, ITE 228, UMBC
A broad reaching brief on some of the technical aspects of DISA’s role as a combat support agency within the Department of Defense. Topics will include Scalability and the challenges of Big Data Analytics, Interoperability of systems, Visualization, Incident Response and Digital Forensics, Challenges with Classification Guidance, Supply Chain Risk Management, and Software Defined Networks/Infrastructure as a Service. Attendees are highly encouraged to ask questions.
James Curry is DISA’s Lead Engineer for the Cyber Security Range (CSR), which is chartered to develop and host a realistic DoD Information Network (DODIN) environment for Training, Testing, or Exercises. In this position, he has designed and built fully virtual implementations of DISA’s Internet Access Points (IAPs) and its Joint Regional Security Stack (JRSS), enabling the DoD Workforce to train in an IaaS on-demand environment that realistically matches DISA’s core infrastructure. He is a Scholarship for Service (SFS) recipient (2008-2009) and received his Masters and Bachelors of Science in Computer Science from New Mexico Tech. Email:
Host: Alan T. Sherman,
The UMBC Cyber Defense Lab meets biweekly Fridays. All meetings are open to the public.
HackUMBC hackathon, Saturday-Sunday 7-8 October 2017
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 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.
The event takes place on Saturday and Sunday, October 7-8 at several locations on the UMBC campus. Visit the HackUMBC site for complete details and to register.
CSEE Alumna Lauren Mazzoli chosen for UMBC Alumni Association Rising Star award
CSEE Alumna Lauren Mazzoli chosen for UMBC Alumni Association Rising Star award
Each year, the UMBC Alumni Association celebrates UMBC graduates and faculty who have made outstanding contributions to the University, their fields, and their communities. This year, CSEE Alumna Lauren Mazzoli was chosen for the Rising Star award, which is given to an outstanding undergraduate alumna/us of the last decade who has demonstrated professional achievement.
Lauren received B.S. degrees in both Computer Science and Mathematics in 2015 and completed a, M.S. degree in Computer Science at UMBC in 2017. As an undergraduate, she was in the first cohort of UMBC’s Cyber Scholars and was a CWIT affiliate. After completing her undergraduate studies, she joined Northrop Grumman as a Cyber Software Engineer and continued her studies in the UMBC Computer Science M.S. program. This summer she was selected for Northrop Grumman’s Future Technical Leaders Program, which is aimed at identifying and investing in Northrop Grumman’s next generation of technologists and leaders.
Lauren has been active as an alumna in supporting UMBC and its programs. She created and ran a semester-long Cyber Competition that was supported by Northrop Grumman for UMBC’s Cyber Scholars and Affiliates and participated in several on-campus activities to strengthen the relationship and interactions between Northrop Grumman and UMBC. She is currently on the board for Northrop Grumman’s Women’s International Network, and was the Lead of the Professional Development Group’s Community Outreach Activities. She has also spoken at, or been a panelist in, a number professional events.
All members of the UMBC community are invited to join the UMBC Alumni Association in celebrating the 2017 award recipients at the 2017 Alumni Awards Ceremony on Thursday, October 5 at 6:30 p.m. in the Earl and Darielle Linehan Concert Hall.
Marie desJardins receives award for inspiring women to pursue careers in computing, engineering and math
Increasing gender diversity in computing has become both a professional focus and personal commitment for desJardins over the course of her career. “It’s part of a broader equity issue — for everyone to be able to envision themselves as creators of technology, and for the future of technology to be created by a diverse community of scientists and engineers,” she says.
This summer, desJardins shared her passion for encouraging girls and women to pursue careers in computing with nearly 150 elementary and middle school girls who attend the Mind, Body, Coding camp at UMBC. “Seeing these young girls whose lives could be transformed by greater access to computing is incredibly inspiring,” she says. “It’s a big part of what gets me energized every day to do the work that I do, from supporting diversity in K-12 computing education to mentoring junior female faculty who will train the next generation of computer scientists.”
The award announcement cited Professor desJardins for her many accomplishments in education, research and support of and commitment to improving student diversity, access, and quality of computer science courses at the high school level.
“Marie is known on campus and throughout her professional community for her dedication to mentoring, diversity, outreach, and innovative educational practices. Marie was named one of UMBC’s 10 “Professors Not to Miss” in 2011, and is regularly sought out to give invited talks to student groups. In 2010, she was invited to be a CRA-W/CDC Distinguished Lecturer. She was also one of the inaugural Hrabowski Innovation Fellows, and with that award, helped to create the ACTIVE Center, a new classroom that supports pedagogical approaches that increase student engagement and active problem solving.
Marie has become known nationally for her support of and commitment to improving student diversity, access, and quality of computer science courses at the high school level, and has received multiple NSF awards to support her efforts in this area. She is the lead PI on the NSF-sponsored “CS Matters in Maryland” project, which is creating curriculum and training high school teachers to teach the new AP CS Principles course. She has built a statewide coalition to increase access to K-12 CS education, with a focus on inclusion and diversity. She is also the Maryland team leader for the Exploring Computing Education Pathways (ECEP) Alliance, an NSF-funded initiative that is coordinating state-level CS education efforts.
Marie is UMBC’s 2014-17 Presidential Teaching Professor and was a founding member of the Maryland chapter of the Computer Science Teachers Association, for which she is currently the university liaison. Her research focuses on artificial intelligence, particularly machine learning, planning and decision making, and multi-agent systems. She has published over 100 scientific papers on these topics, and was recently named one of the “Ten AI Researchers to Follow on Twitter” by TechRepublic and one of “14 Women in AI You Should Follow on Twitter” by craigconnects.
At UMBC, Marie has been PI or co-PI on over $6,000,000 of external research funding, including a prestigious NSF CAREER Award, and has graduated 11 Ph.D. students and 25 M.S. students. She is particularly well known on campus and in her professional community for her commitment to student mentoring. She has been involved with the AAAI/SIGART Doctoral Consortium for the last 16 years and has worked with 90 undergraduate researchers and high school student interns. She was awarded the 2014 NCWIT Undergraduate Research Mentoring Award and the 2016 CRA Undergraduate Research Mentoring Award in recognition of her commitment to undergraduate research.”
UMBC researchers develop AI system to design clothing for your personal fashion style
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!
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.
Prof. Cynthia Matuszek on how robots could help bridge the elder-care gap
Despite innovations that make it easier for seniors to keep living on their own rather than moving into special facilities, most elderly people eventually need a hand with chores and other everyday activities.
So how will our society bridge this elder-care gap? In a word, robots.
Just as automation has begun to do jobs previously seen as uniquely suited for humans, like retrieving goods from warehouses, robots will assist your elderly relatives. As a robotics researcher, I believe artificial intelligence has the potential not only to care for our elders but to do so in a way that increases their independence and reduces their social isolation.
In the 2004 movie “I, Robot,” the robot-hating protagonist Del Spooner (played by Will Smith) is shocked to discover a robot in his grandmother’s house, baking a pie. You may have similar mental images: When many people imagine robots in the home, they envision mechanized domestic workers doing tasks in human-like ways.
In reality, many of the robots that will provide support for older adults who “age in place” – staying at home when they might otherwise be forced to relocate to assisted living or nursing homes – won’t look like people.
Instead, they will be specialized systems, akin to the Roomba, iRobot’s robotic vacuum cleaner and the first commercially successful consumer robot. Small, specific devices are not only easier to design and deploy, they allow for incremental adoption as requirements evolve over time.
Seniors, like everyone else, need different things. Many need help with the mechanics of eating, bathing, dressing and standing up – tasks known as “activities of daily living.” Along with daily help with cooking and managing their medications, they can benefit from a robotic hand with more intermittent things such as doing the laundry and getting to the doctor’s office.
Meanwhile, robot companions may soon help relieve loneliness and nudge forgetful elders to eat on a regular schedule.
Scientists and other inventors are building robots that will do these jobs and many others.
While some tasks remain out of reach of today’s robots, such as inserting IVs or trimming toenails, mechanical caregivers can offer clear advantages over their human counterparts.
The most obvious one is their capacity to work around the clock. Machines, unlike people, are available 24/7. When used in the home, they can support aging in place.
Another plus: Relying on technology to meet day-to-day needs like mopping the floor can improve the quality of time elders spend with family and friends. Delegating mundane chores to robots also leaves more time for seniors to socialize with the people who care about them, and not just for them.
And since using devices isn’t the same as asking someone for help, relying on caregiving robots may lead seniors to perceive less lost autonomy than when they depend on human helpers.
Interacting with robots
This brave new world of robot caregivers won’t take shape unless we make them user-friendly and intuitive, and that means interaction styles matter. In my lab, we work on how robots can interact with people by talking with them. Fortunately, recent research by the Pew Research Center shows that older adults are embracing technology more and more, just like everyone else.
Now that we are beginning to see robots that can competently perform some tasks, researchers like Jenay Beer, an assistant professor of computer science and engineering at the University of South Carolina, are trying to figure out which activities seniors need the most help with and what kinds of robots they might be most willing to use in the near term.
To that end, researchers are asking questions like:
But the fact is we don’t need all the answers before robots begin to help elders age in place.
After all, there’s no time to lose.
The Census Bureau estimated that 15 percent of Americans – nearly one in six of us – were aged 65 or older in 2016, up from 12 percent in 2000. Demographers anticipate that by 2060 almost one in four will be in that age group. That means there will be some 48 million more elderly people in the U.S. than there are now.
I believe robots will perform many elder-care tasks within a decade. Some activities will still require human caregivers, and there are people for whom robotic assistance will never be the answer. But you can bet that robots will help seniors age in place, even if they won’t look like butlers or pastry chefs.
Prof. Gymama Slaughter to develop bioreactors for life-saving organ transplants
UMBC’s Gymama Slaughter to develop bioreactors that could pause the clock for life-saving organ transplants
UMBC’s Gymama Slaughter will develop a bioreactor to extend the viability of lifesaving human organs as they await transplant through a major new grant from the U.S. Army Medical Research and Material Command. Funding for the project totals nearly $1.5 million for a period of three years. Slaughter, associate professor of computer science and electrical engineering, will collaborate closely with Warren Grayson and Gerald Brandacher, both associate professors at Johns Hopkins.
The team will create a bioreactor integrating in-line sensors, mechanical stimulator, and blood perfusion system to more accurately and continuously monitor organs as they are transported for transplantation. They will also “develop a system that closely mimic the organ’s natural environment,” explains Slaughter.
Currently, organ and tissue donors typically need to be in close proximity to transplant recipients due to limitations in organ transport. Some organs are only viable for about six hours, and they must be kept at very cool temperatures to remain viable, so the transport process can be a race against time. With technological improvements, Slaughter says, the viability of the organs could be increased to about 36 hours, greatly expanding the distance an organ could travel from donor to recipient, and the likelihood of a successful transplant.
“This interdisciplinary research will enable us to tackle complex organ transplant viability problems to create the next big breakthrough platform technology for extending and monitoring the viability of organs to improve patient care,” says Slaughter. Together, the researchers hope their work will lead to a new era of successful human organ transplantation, saving the lives of wounded soldiers and others in need of transplants in hard-to-reach locations around the world.
PhD defense: Prajit Das, Context-dependent privacy and security management on mobile devices
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)
PhD Defense: Bryan Wilkinson, Identifying and Ordering Scalar Adjectives using Lexical Substitution
Ph.D. Dissertation Defense
Identifying and Ordering Scalar Adjectives using Lexical Substitution
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)
talk: Sarit Kraus on Computer Agents that Interact Proficiently with People, Noon Fri 8/4
Computer Agents that Interact Proficiently with People
Prof. Sarit Kraus
Deptartment of Computer Science, Bar-Ilan University
Ramat-Gan, 52900 Israel
12:00-1:00pm Friday, 4 August 2017, ITE ITE 217B, UMBC
Automated agents that interact proficiently with people can be useful in supporting, training or replacing people in complex tasks. The inclusion of people presents novel problems for the design of automated agents strategies. People do not necessarily adhere to the optimal, monolithic strategies that can be derived analytically. Their behavior is affected by a multitude of social and psychological factors. In this talk I will show how combining machine learning techniques for human modeling, human behavioral models, formal decision-making and game theory approaches enables agents to interact well with people. Applications include intelligent agents that help drivers reduce energy consumption, agents that support rehabilitation, employer-employee negotiation and agents that support a human operator in managing a team of low-cost mobile robots in search and rescue task
Sarit Kraus (Ph.D. Computer Science, Hebrew University, 1989) is a Professor and is the Department Chair of Computer Science at Bar-Ilan University. Her research is focused on intelligent agents and multi-agent systems (including people and robots). In particular, she studies the development of intelligent agents that can interact proficiently with people. She studies both cooperative and conflicting scenarios. She considers modeling human behavior and predicting their decisions necessary for facing these challenges as well as the development of formal models for the agent’s decision making. She has also contributed to the research on agent optimization, homeland security, adversarial patrolling, social networks and nonmonotonic reasoning.
For her pioneer work she received many prestigious awards. She was awarded the IJCAI Computers and Thought Award, the ACM SIGART Agents Research award, the EMET prize and was twice the winner of the IFAAMAS influential paper award. She is an ACM, AAAI and ECCAI fellow and a recipient of the advanced ERC grant. She also received a special commendation from the city of Los Angeles, together with Prof. Tambe, Prof. Ordonez and their USC students, for the creation of the ARMOR security scheduling system. She has published over 350 papers in leading journals and major conferences. She is the author of the book “Strategic Negotiation in Multiagent Environments” (2001) and a co-author of the books “Heterogeneous Active Agents” (2000) and “Principles of Automated Negotiation” (2014). Kraus is a senior associate editor of the Annals of Mathematics and Artificial Intelligence Journal and an associate editor of the Journal of Autonomous Agents and Multi-Agent Systems and of JAIR. She is a member of the board of directors of the International Foundation for Multi-agent Systems (IFAAMAS).