The UMBC Cyber Defense Lab presents

Moving Target Mobile IPv6 Defense

Prof. Vahid Heydari
Computer Science, Rowan University

12:00–1 pm ET, Friday, 26 February 26, 2021

remotely via WebEx  

Remote cyberattacks can be started from an unlimited distance through the Internet. These attacks include particular actions that allow attackers to compromise systems remotely. Address-based Distributed Denial-of-Service (DDoS) attacks and remote exploits are two main categories of these attacks. A remote exploit takes advantage of a bug or vulnerability to view or steal data or gain unauthorized access to a vulnerable system. Current security solutions in IPv6 such as IPsec, firewall, and Intrusion Detection and Prevention System (IDPS) can prevent remote attacks against known vulnerability exploits. However, zero-day exploits can defeat the best firewalls and IDPSs due to using undisclosed and uncorrected computer application vulnerability. Therefore, a new solution is needed to prevent these attacks. This talk discusses a Moving Target Mobile IPv6 Defense (MTM6D) that randomly and dynamically changes the IP addresses to prevent remote attacks in the reconnaissance step. The talk briefly covers the wide range of applications of MTM6D including critical infrastructure networks, virtual private networks, web servers, Internet-controlled robots, and anti-censorship.

 Vahid Heydari received the M.S. degree in Cybersecurity and the Ph.D. degree in Electrical and Computer Engineering from the University of Alabama in Huntsville. He is currently an Associate Professor of Computer Science and the Director of the Center for Cybersecurity Education and Research at Rowan University, Glassboro, NJ. He is also a co-founder of a cybersecurity startup ObtegoCyber. His research interests include moving target defenses, mobile ad-hoc, sensor, and vehicular network security. He is a member of ACM, IEEE Computer Society and Communications Society. 

Host: Alan T. Sherman, , Support for this event was provided in part by the National Science Foundation under SFS grant DGE-1753681. The UMBC Cyber Defense Lab meets biweekly Fridays.  All meetings are open to the public. Upcoming CDL Meetings:

Mar 12, Chao Liu (UMBC), Efficient asynchronous BFT with adaptive security
Mar 26, Jeremy Clark (Concordia)
April 9, (UMBC), MeetingMayhem: A network adversarial thinking game
April 23, Peter Peterson (University of Minnesota Duluth), Adversarial thinking
May 7, Farid Javani (UMBC), Anonymization by oblivious transfer

Professor Anthony Johnson selected as the 2021 recipient of The Optical Society Stephen D. Fantone Distinguished Service Award

CSEE Professor Anthony Johnson has been selected as the 2021 recipient of The Optical Society (OSA) Stephen D. Fantone Distinguished Service Award. Dr. Johnson is being honored specifically for decades of principled leadership and steadfast service to The Optical Society and to the optics community, and especially for serving as a tireless ambassador for OSA.

Dr. Johnson has served in numerous leadership roles for OSA, including Director-at-Large on OSA’s Board of Directors, chair of the Women & Minorities Committee, and chair of the Awards Council. He was the 2002 OSA President, and continues to remain active with OSA. He currently sits on the Presidential Advisory Committee (PAC) and serves as a member of the OSA Diversity, Equity and Inclusion Rapid Action Committee (DEI RAC). In addition to his service to OSA, Johnson is an active leader in the National Society of Black Physicists, American Physical Society (APS), and IEEE, and he supported the African Laser Atomic, Molecular, and Optical Sciences Network (LAM Network) by establishing the African Optics and Photonics Society.

Founded in 1916, OSA is the leading professional organization for scientists, engineers, students and business leaders who fuel discoveries, shape real-life applications and accelerate achievements in the science of light. Through world-renowned publications, meetings and membership initiatives, OSA provides quality research, inspired interactions and dedicated resources for its extensive global network of optics and photonics experts.

This award was established in 1973 by the Board of Directors. It is presented to a recipient who, over an extended period of time, has served the Optical Society in an outstanding way, especially through volunteer participation in its management, operation, or planning in such ways as editorship of a periodical, organization of meetings, or other service to the Society. He joins an esteemed group of past recipients recognized for their outstanding contributions, service, and leadership in the field of optics and photonics.

A press release announcing several 2021 award winners is available, as well as an announcement about the 2021 Stephen D. Fantone Distinguished Service Award.

Three CSEE faculty receive MIPS research awards

This post is adapted from a UMBC News article UMBC faculty, alumni entrepreneurs receive record-number of MIPS awards for tech collaborations written by Adriana Fraser.

Six UMBC faculty members have just received grants from the Maryland Industrial Partnerships (MIPS) program to develop new technologies with potential to grow the state’s economy. This is UMBC’s largest number of winning proposals within a single proposal round since MIPS began in 1987. The program connects University System of Maryland (USM) faculty and students with Maryland businesses. UMBC’s latest MIPS grantees include computer science and electrical engineering faculty Tim Oates, Chein-I Chang, and Anupam Joshi; Soobum Lee, mechanical engineering; Dipanjan Pan, chemical, biochemical, and environmental engineering; and Vikram Vakharia, marine biotechnology. Among their industry partners are UMBC alumni entrepreneurs who are building businesses in Maryland.

Joshi, professor and chair of computer science and electrical engineering, received a MIPS grant for a cybersecurity collaboration with the startup CyDeploy. They are developing a platform that automates the quality assurance process for cybersecurity updates made to IT and “internet of things” (IoT) devices like Amazon Alexa, Google Home, and health and medical devices. CyDeploy CEO Tina Williams-Koroma ’02, computer science, presented Joshi with the idea to develop a “cybersecurity-driven change management system.” The technology is based on and leverages the use of artificial intelligence and machine learning to create a cloud-based replica of a company’s systems. 

Williams-Koroma and Joshi’s group at UMBC developed a conceptual prototype. It shows the infrastructure and technology that would make the system feasible, combining off-the-shelf tools with novel research. “Increasingly, the government is now beginning to mandate security requirements around IoT devices. The longer-term vision that CyDeploy has is capturing the state of these systems, virtually recreating them and then running the security changes against virtual versions to see how the changes would affect those systems,” Joshi adds. 

Williams-Koroma, who is also an adjunct instructor at UMBC, projects that the initial development of the platform will be complete in late spring 2021. They anticipate launching a free pilot version for businesses to test their IT systems. IoT pilots will come in a later phase.

Read more about these awards in the UMBC News article UMBC faculty, alumni entrepreneurs receive record-number of MIPS awards for tech collaborations.

UMBC Information Systems Department

Machine Learning for Malware:
Challenges and Progress 

Dr. Edward Raff
Booz Allen Hamilton
Visiting Prof. UMBC Computer Science & Electrical Engineering

12:00-1:00 pm ET Wednesday, 17 February 2021

online via WebEx

Malware is an ever-growing problem, single malware families have caused billions in damages, and the first direct death attributed to malware taking down a hospital has occurred. To detect new malware, machine learning is a naturally attractive approach. However, malware poses a number of unique challenges that have slowed the progress of ML-based solutions. In this talk, we will look at the task of malware detection from byte-based analysis, why it poses many challenging machine learning research problems, and progress we have made on these tasks by taking some non-standard approaches to machine learning: building shallow and wide networks instead of deep, handicapping the features of our model to make it robust, and using literal compression algorithms (LZMA) to find similar content. 

Edward Raff leads Booz Allen’s machine learning research group and supports clients in developing new ML solutions. His research includes cybersecurity, adversarial machine learning, fairness and ethics, fingerprint biometrics, and high-performance computing. In his spare time, he is the author of the JSAT machine learning library. He received his BS and MS in Computer Science from Purdue University and his Ph.D. in CS from UMBC. Dr. Raff is a Nvidia Deep Learning certified instructor, and Visiting Professor at UMBC.

CARTA Distinguished Lecture

Modeling and Simulation for
Reducing the Risks Associated with
Extreme Weather

Dr. Robert Atlas

Research Professor & Global Coordinator for CARTA
Director Emeritus/ NOAA Atlantic Oceanographic and Meteorological Laboratory

 11:00-12:00 ET Wednesday, 10 February 2021

WebEX link

The reduction of losses related to hurricanes and other extreme weather phenomena involves many complex aspects ranging from purely theoretical, observational, computational, and numerical, to operational and decisional. A correct warning can lead to proper evacuation and damage mitigation, and produce immense benefits. However, over-warning can lead to substantial unnecessary costs, a reduction of confidence in warnings, and a lack of appropriate response. In this chain of information, the role played by scientific research is crucial.

The National Oceanic and Atmospheric Administration (NOAA), in combination with the National Aeronautics and Space Administration (NASA), other agencies, and universities is contributing to these efforts through observational and theoretical research to better understand the processes associated with extreme weather. This includes model and data assimilation development, Observing System Experiments (OSE), and Observing System Simulation Experiments (OSSE) designed to ascertain the value of existing observing systems and the potential of new observing systems to improve weather prediction and theoretical understanding. This high-level talk, which was first given as the Keynote address at the 2019 Winter Simulation Conference, will describe innovative research for developing advanced next-generation global and regional models to improve weather prediction, and the application of OSSEs to optimize the observing system.

Dr. Robert Atlas is the former Chief Meteorologist at NASA’s Goddard Laboratory for Atmospheres and is Director Emeritus of the National Oceanic and Atmospheric Administration’s (NOAA) Atlantic Oceanographic and Meteorological Laboratory in Miami, Fla. Some of the areas he focused his research on included the prediction, movement, and strengthening of hurricanes. He has worked with both satellite data and computer models as a means to study these hurricane behaviors.

Dr. Atlas received his Ph.D. in Meteorology and Oceanography in 1976 from New York University. Prior to receiving the doctorate, he was a weather forecaster in the U.S. Air Force where he maintained greater than 95 percent forecast accuracy. From 1976 to 1978, Dr. Atlas was a National Research Council Research Associate at NASA’s Goddard Institute for Space Studies, New York, an Assistant Professor of Atmospheric and Oceanic Science for SUNY, and Chief Consulting Meteorologist for the ABC television network.

In 1978, Dr. Atlas joined NASA as a research scientist. He served as head of the NASA Data Assimilation Office from 1998-2003, and as Chief meteorologist at NASA GSFC from 2003-2005. Dr. Atlas has performed research to assess and improve the impact of satellite data on numerical weather prediction since 1973. He was a key member of the team that first demonstrated the significant impact of quantitative satellite data on numerical weather prediction and is the world’s leading expert on Observing System Simulation Experiments, a technology that enables scientists to determine the quantitative value of new observing systems before funds are allocated for their development.

He served as a member of the Satellite Surface Stress Working Group, the NASA Scatterometer (NSCAT) Science Team, the ERS Science Team, the SeaWinds Satellite Team, the Working Group for Space-based Laser Winds, the Scientific Steering Group for GEWEX, the Council of the American Meteorological Society, and as Chairman of the U.S. World Ocean Circulation Experiment (WOCE) Advisory Group for model-based air-sea fluxes. He is currently a member of the Science Teams for two NASA space missions.

From 1974-1976, he developed a global upper-ocean model and studied oceanic response to atmospheric wind forcing as well as large-scale atmospheric response to sea surface temperature (SST) anomalies (unusual events). In more recent years, his research concentrated on the role of how the air and sea interact in the development of cyclones, the role of soil moisture and unusual SST events in the initiation, maintenance, and decay of prolonged heatwaves and drought, and most recently on the modeling and prediction of hurricane formation, movement, and intensification.

He is a recipient of the NASA Medal for Exceptional Scientific Achievement and the American Meteorological Society’s Banner I. Miller Award. In 2019, just prior to his retirement from NOAA, he was honored by the National Hurricane Center for Enduring Contributions to the nation’s hurricane forecast and warning program, and by the U.S. House of Representatives for his service to the nation.

The UMBC Cyber Defense Lab presents

Startup Lessons Learned

Richard Carback (Ph.D. UMBC CS 2010)
xx network

12:00–1:00pm ET, Friday,12 February 12 2021
WebEx: https://umbc.webex.com/meet/sherman

This talk will explore the technology and lessons learned by UMBC alumnus Richard Carback from his experience co-founding and closing the security startup Lexumo, which provided the only automated service that continuously monitors IoT software platforms for the latest public vulnerabilities. In addition to covering some of the hard problems and Lexumo’s technical approach for monitoring all the world’s open-source software to assist companies in managing their vulnerabilities, Dr. Carback will discuss the mistakes and complexities of getting funded, delivering a product, and finding customers.

Dr. Richard Carback is a UMBC Alumnus (CS Ph.D., 2010) who is an entrepreneur who currently runs a private consultancy for computer security, computer forensics, cryptography, and smart contracts. He is a privacy-preserving systems expert with a background in elections and anonymity networks. While the group leader for the embedded systems security group at Charles Stark Draper Laboratories, he spun out an IoT vulnerability startup called Lexumo that provided the only automated service that continuously monitored IoT software platforms for the latest public vulnerabilities. At UMBC, he worked with Alan Sherman on secure elections and was the primary researcher behind Takoma Park’s deployment of the Scantegrity voting system, the first usage of voter-verifiable end-to-end election technology in a municipal election. email:

Host: Alan T. Sherman, . Support for this event was provided in part by the NSF under SFS grant DGE-1753681. The UMBC Cyber Defense Lab meets biweekly Fridays 12-1 pm. All meetings are open to the public. Upcoming CDL Meetings:

• Feb 26, Vahid Heydari (Rowan University)
• Mar 12, Chao Liu (UMBC), Efficient asynchronous BFT with adaptive security
• Mar 26, Jeremy Clark (Concordia)
• April 9, (UMBC), MeetingMayhem: A network adversarial thinking game
• April 23, Peter Peterson (University of Minnesota Duluth), Adversarial thinking
• May 7, Farid Javani (UMBC), Anonymization by oblivious transfer

Two UMBC alumnae featured in The CyberWire podcast

The CyberWire produced a special podcast, In the clear: what it’s like working as a woman in the cleared community, that features three women working on cybersecurity at Northrop Grumman. Two are UMBC alumnae, software engineering manager Lauren and cyber software engineer Priyanka.

Lauren received a BS in Computer Science in 2015 and an M.S. in Computer Science in 2017. As an undergraduate student, she worked part-time as an IT Security Analyst tracking, locating, and performing forensics on infected computers located on campus. She joined Northrop Grumman in 2015 and continued her studies as a part-time graduate student, doing research on investigating different ways of characterizing cybersecurity exploit kits and the malware they produce.

Priyanka received a BS in Computer Science in 2018 and an MS in Computer Science in 2019. Her MS research was on multilingual text alignment for cybersecurity. She has been a lecture in the UMBC Computer Science program and the UMD Advanced Cybersecurity Experience for Students (ACES) program. She is currently working on a Computer Science Ph.D. at UMBC focused on how AI can help protect cybersecurity systems from data poisoning attacks.

Listen to the 47 minute podcast here.

Theoryful Machine Learning
in the Chemical Sciences

Prof. Tyler R. Josephson

ATOMS Lab: AI & Theory-Oriented Molecular Science
Chemical, Biochemical & Environmental Engineering, UMBC

1:00-2:00 pm, 5 February 2021
online via webex

Modern machine learning (ML) algorithms have achieved remarkable success in “theoryless” problems of image recognition and natural language processing. When these algorithms find applications in “theoryful” domains like physical sciences, they frequently benefit from the incorporation of domain knowledge into the ML architecture, whether enforcing constraints or symmetries or interpreting neural networks as physical systems.

The chemical sciences have many “theoryful” ML problems. In this talk, I will discuss three projects in which we leverage background theory when designing and adopting ML algorithms. In the first project, we use classical thermodynamics to derive a method to characterize mixture properties in molecular simulations and show that multiple linear regression (with no bias) is the formally correct and thermodynamically consistent model for fitting and predicting these properties. We recently developed an alternative proof from statistical thermodynamics that gives the same result, and we provide evidence that nonlinear methods provide no improvement in performance. In the second project, we perform high-throughput molecular simulations of adsorption (when molecules from a gas or liquid stick on the surface or in the pores of a material), which we analyze using neural networks. We derive a correspondence between theories of multicomponent adsorption and the self-attention mechanism in the transformer architecture and show how the theory-inspired architecture has improved generalization over the multilayer perceptron.

In the final project, I will share work on symbolic regression, in collaboration with the Mathematics of AI department at IBM. In symbolic regression, given a data set, a search through some “space of possible equations” identifies accurately-fitting and parsimonious equations that can be easily inspected by humans. We formulate the symbolic regression problem as a mixed-integer nonlinear programming (MINLP) problem and use MINLP solvers to systematically solve multiple functional forms at once, instead of via the traditional approaches that use genetic algorithms. Future approaches to integrate symbolic regression with chemical theory will be discussed.

Tyler R. Josephson is an Assistant Professor in the Chemical, Biochemical, and Environmental Engineering department at the University of Maryland, Baltimore County. He received his B.S. in Chemical Engineering from the University of Minnesota in 2011, and his Ph.D. in Chemical Engineering from the University of Delaware in 2017, after which he was a postdoctoral associate in the University of Minnesota Chemistry Department. Prof. Josephson uses multi-scale modeling and machine learning to study catalysis, solvation, adsorption, and phase equilibria. During his downtime, he loves learning new things, thinking about deep topics (like science and philosophy), and playing the piano.

Visiting Prof. Ed Raff’s forthcoming book Inside Deep Learning

Congratulation to Dr. Edward Raff for his forthcoming book Inside Deep Learning being published by Manning. The first three chapters are now available free online via Manning’s Early Access Program, with more to come. Dr. Raff is a Chief Scientist at Booz Allen Hamilton and both an alumnus of and visiting assistant professor in the UMBC CSEE department. 

He describes the target audience for his book as “the middle between “give me a tool” and ‘CS/Stats/ML Ph.D. graduate book’ that gives utility and understanding.” He gives thanks to his UMBC students in his Computer Science and Data Science classes who have been “guinea pigs for this book/course material.”

Here’s how the publisher describes the book: “Inside Deep Learning is a fast-paced beginners guide to solving common technical problems with deep learning. Written for everyday developers, there are no complex mathematical proofs or unnecessary academic theory. You’ll learn how deep learning works through plain language, annotated code, and equations as you work through dozens of instantly useful PyTorch examples. As you go, you’ll build a French-English translator that works on the same principles as professional machine translation and discover cutting-edge techniques just emerging from the latest research. Best of all, every deep learning solution in this book can run in less than fifteen minutes using free GPU hardware!”

Ed Raff received a Ph.D. in Computer Science in 2018 with a dissertation on “Malware Detection and Cyber Security via Compression.” He is currently a Chief Scientist at Booz Allen Hamilton. He has done research on deep learning, malware detection, reproducibility in machine learning, detecting fairness and bias in machine learning models and data analytics, and high-performance computing. He has also been a visiting Assistant Professor at UMBC since 2018 and taught in both the Computer Science and Data Science programs. Dr. Raff has over 40 peer-reviewed publications, three best paper awards, and has presented at many major conferences.