Electrical Engineering and Computer Science

CSE Research News

Manos Kapritsos and Collaborators Win USENIX Security Paper Award

A team of researchers including Prof. Manos Kapritsos has won a Distinguished Paper Award at the 2017 USENIX Security Symposium for Vale, a new programming language and tool that supports flexible, automated verification of high-performance cryptographic assembly code. [Full Story]

Related Topics:  Cryptography  Kapritsos, Manos  Lab-Software Systems  

Michigan, Georgia Tech Researchers Funded to Deter Financial Market Manipulation

Researchers at the University of Michigan and the Georgia Institute of Technology will develop innovative approaches to detecting and deterring the computerized manipulation of financial markets under a $1M grant from the National Science Foundations's Big Data program. Michael Wellman, the Lynn A. Conway Collegiate Professor of Computer Science and Engineering, is project director and one of five PIs. [Full Story]

Related Topics:  Artificial Intelligence  Big Data  Economic Systems  Lab-Artificial Intelligence  Wellman, Michael  

Improving Natural Language Processing with Demographic-Aware Models

Michigan researchers, including Prof. Rada Mihalcea, research fellow Carmen Banea, and graduate student Aparna Garimella have found that word associations vary across different demographics, and researchers can build better natural language processing models if they can account for demographics. [Full Story]

Related Topics:  Lab-Artificial Intelligence  Mihalcea, Rada  

BugMD: Automatic Mismatch Diagnosis for Bug Triaging

Today's incredibly dense microprocessors take more time to verify for correctness than they do to design, and bugs are extremely difficult to track down and correct. CSE researchers have introduced BugMD, an automatic bug triaging solution that collects multiple architectural-level mismatches and employs a classifier to pinpoint buggy design units. [Full Story]

Related Topics:  Bertacco, Valeria  Computer Architecture  Computer-Aided Design & VLSI  Lab-Computer Engineering (CE Lab)  Mahlke, Scott  

'Learning Database' Speeds Queries from Hours to Seconds

University of Michigan researchers developed software called Verdict that enables existing databases to learn from each query a user submits, finding accurate answers without trawling through the same data again and again. Verdict allows databases to deliver answers more than 200 times faster while maintaining 99 percent accuracy. In a research environment, that could mean getting answers in seconds instead of hours or days. [Full Story]

Related Topics:  Big Data  Lab-Software Systems  Mozafari, Barzan  

Codeon is the Intelligent Assistant for Software Developers

Researchers, including Profs. Walter S. Lasecki and Steve Oney, and graduate students Yan Chen and Yin Xie have created Codeon, a system that enables more effective task hand-off between end-user developers and remote helpers by allowing asynchronous responses to on-demand requests. With Codeon, developers can request help by speaking their requests aloud within the context of their Integrated Development Environment. [Full Story]

Related Topics:  Lab-Artificial Intelligence  Lab-Software Systems  Lasecki, Walter  

Accelerating the Mobile Web: Vroom Software Could Double its Speed

Vroom software, developed by computer scientists including Prof. Harsha Madhyastha and CSE graduate student Vaspol Ruamviboonsuk, can dramatically speed the loading of webpages on mobile devices. [Full Story]

Related Topics:  Lab-Software Systems  Madhyastha, Harsha  Mobile Computing  

Kurator Will Help You Curate Your Personal Digital Content

People capture photos, audio recordings, video, and more on a daily basis, but organizing all these digital artifacts quickly becomes a daunting task. Automated solutions struggle to help us manage this data because they cannot understand its meaning. Profs. Walter Lasecki and Mark Ackerman have helped create Kurator, a hybrid intelligence system leveraging mixed-expertise crowds to help families curate their personal digital content. [Full Story]

Related Topics:  Ackerman, Mark  Lab-Artificial Intelligence  Lab-Software Systems  Lasecki, Walter  

Movie Design for Specific Target Audiences

Creating products that satisfy the market is critical to companies as it determines their success and revenue. Currently, experts use their judgment to estimate solutions to designing a new product that will satisfy customers, but this does not scale or allow leveraging massive datasets. Prof. Danai Koutra and her colleagues sought to identify how they can design new movies with features tailored to a specific user population. [Full Story]

Related Topics:  Koutra, Danai  Lab-Artificial Intelligence  Lab-Software Systems  

CHORUS: The Crowd-Powered Conversational Assistant

Prof. Walter Lasecki and his colleagues have developed a crowd-powered conversational assistant, Chorus, and deployed it to see how users and workers would interact together when mediated by the system. Chorus is capable of providing users with relevant responses instead of merely search results by recruiting workers on demand, who in turn decide what the best response is for each user sentence. [Full Story]

Related Topics:  Lab-Artificial Intelligence  Lab-Software Systems  Lasecki, Walter  

Social Interaction Patterns Provide Clues to Real Life Changes

Researchers including Prof. Danai Koutra have explored the dynamics of individual user interactions in social networks by creating iNET, a comprehensive analytic and visualization framework that provides personalized insights into user behavior. The researchers view their work as a first step towards fully exploring the amount and type of information that can be extracted from the online social footprint of a person. [Full Story]

Related Topics:  Koutra, Danai  Lab-Artificial Intelligence  Lab-Software Systems  

Apps available for your smartphone could steal your personal information

WXYZ Detroit reports on work by UM researchers that has exposed dangerous open ports in mobile platforms that can be taken advantage of by hackers. [Full Story]

Related Topics:  Graduate Students  Lab-Software Systems  Mao, Zhuoqing Morley  Mobile Computing  Security (Computing)  

Breakthrough for Large Scale Computing: Memory Disaggregation Made Practical

CSE researchers have introduced Infiniswap, the first system to scalably implement cluster-wide memory disaggregation, whereby the memory of all the servers in a computing cluster is transparently exposed as a single memory pool to all the applications in the cluster. [Full Story]

Related Topics:  Chowdhury, Mosharaf  Lab-Software Systems  Networking, Operating Systems, and Distributed Systems  Shin, Kang G.  Software Systems  

Open Ports Act As Security Wormholes Into Mobile Devices

Computer science and engineering researchers at the University of Michigan have for the first time characterized a widespread vulnerability in the software that runs on mobile devices which could allow attackers to steal contact information, security credentials, photos, and other sensitive data, and also to install malware and to perform malicious code execution which could be used in large-scale attacks. [Full Story]

Related Topics:  Graduate Students  Lab-Software Systems  Mao, Zhuoqing Morley  Mobile Computing  Networking, Operating Systems, and Distributed Systems  Security (Computing)  

Video: Tech Time - Software developed to help the blind

This news segment on WDIV TV highlights the work that Dr. David Chesney and his students have done in conjunction with India West, a passionate young woman who lost her eyesight at an early age. Together, they conceptualize and develop technology for the visually impaired. [Full Story]

Related Topics:  Chesney, David  Engineering for the Greater Good  Undergraduate Students  

Sonic Cyber Attacks Show Security Holes in Ubiquitous Sensors

Sound waves can be used to hack into critical sensors used in a broad array of technologies including smartphones, automobiles, medical devices, and the Internet of Things, according to research performed by Prof. Kevin Fu, Prof. Peter Honeyman, CSE graduate student Timothy Trippel, and their collaborators at the University of South Carolina. [Full Story]

Related Topics:  Embedded Computing and Systems  Fu, Kevin  Graduate Students  Internet of Things  Lab-Computer Engineering (CE Lab)  Lab-Software Systems  Security (Computing)  

CSE-Based Startup Clinc Receives $6.3M in Funding to Further Develop Intelligent Banking Assistant

Clinc, the cutting-edge artificial intelligence startup founded by Profs. Jason Mars and Lingjia Tang along with CSE research fellow Michael Laurenzano and CSE graduate student Johann Hauswald, has announced it has closed a $6.3 million Series A round of financing. [Full Story]

Related Topics:  Artificial Intelligence  Lab-Artificial Intelligence  Mars, Jason  Tang, Lingjia  Technology Transfer  

Harsha Madhyastha Selected for Google Faculty Award

Prof. Harsha V. Madhyastha has been awarded a 2017 Google Faculty Research Award for his work in enabling the deployment of low-latency web services in the cloud. It is his third research award from Google. [Full Story]

Related Topics:  Cloud Computing  Data Centers  Lab-Software Systems  Madhyastha, Harsha  Networking, Operating Systems, and Distributed Systems  Software Systems  

Google-funded Flint Water App Helps Residents Find Lead Risk, Resources

Faculty and students at Michigan's Ann Arbor and Flint campuses have released an app that provides Flint residents with data about the ongoing water crisis. The app was developed with support from Google.org. [Full Story]

Related Topics:  Abernethy, Jake  Big Data  Lab-Artificial Intelligence  Machine Learning  

Professor to Congress: "Internet of Things security is woefully inadequate"

As the Internet of Things grows around us, so do the threat of cybersecurity breaches severe enough to shut down hospitals and other vital infrastructure. This is the message that Prof. Kevin Fu delivered to lawmakers at a congressional hearing this week. [Full Story]

Related Topics:  Fu, Kevin  Lab-Computer Engineering (CE Lab)  Security (Computing)  

Kevin Fu Testifies on the Role of Connected Devices in Recent Cyber Attacks

Prof. Kevin Fu testified before the House Energy and Commerce Committee on the role of connected devices in recent cyber attacks on Wednesday, Nov 16, 2016. Follow the link to see a video of the proceedings. [Full Story]

Related Topics:  Fu, Kevin  Lab-Computer Engineering (CE Lab)  Security (Computing)  

Harsha Madhyastha Selected for Facebook Faculty Award

Prof. Harsha V. Madhyastha has been selected as the recipient of a Facebook Faculty Award for his work in distributed systems and computer networking. His recent research has focused on enabling latency-sensitive web services to optimize user experience. [Full Story]

Related Topics:  Lab-Software Systems  Madhyastha, Harsha  Networking, Operating Systems, and Distributed Systems  

Using cyber security to keep your ballot safe ahead of the presidential election

This TV news segment features an interview with CSE graduate student Matthew Bernhard. He is interviewed about the possibility for stolen votes in the upcoming election. His answer: Michigan has a paper ballot/optical scan system, which is considered best practice. Touchscreen, paperless systems like those in Ohio, Virginia, and some other states are not secure enough yet. [Full Story]

Related Topics:  Digital Democracy  Graduate Students  Lab-Software Systems  Security (Computing)  

Jia Deng Selected as Recipient of PAMI Mark Everingham Prize

Prof. Jia Deng has won the PAMI Everingham Prize for his work in developing ImageNet, a large-scale labeled image database that has powered many recent advances in computer vision. The award is presented at the ECCV Conference to a researcher, or a team of researchers, who have made a selfless contribution of significant benefit to other members of the computer vision community. [Full Story]

Related Topics:  Computer Vision  Deng, Jia  Lab-Artificial Intelligence  

COVE: A Tool for Advancing Progress in Computer Vision

A new project has been launched to provide open and easy access to up-to-date, varied, data sets, annotations and their relevant tools. Based at the University of Michigan with collaborators at Boston University and the University of Notre Dame, the program aims to centralize available data in the intelligent systems community through a COmputer Vision Exchange for Data, Annotations and Tools, called COVE. The project promises to have an immediate and far-reaching impact on the computer vision community as well as researchers involved in machine learning, multimedia, natural language processing, data mining, and information retrieval. [Full Story]

Related Topics:  Computer Vision  Corso, Jason  Lab-Systems  Signal & Image Processing and Machine Learning  

Shadows in the Dark Web

Secrets lurk in the dark web, the 95 percent of the internet that most of us can't see. Prof. Michael Cafarella is bringing some of those secrets to light, and in the process making the digital and the real world a little safer. [Full Story]

Related Topics:  Big Data  Cafarella, Michael  Lab-Software Systems  

How big data and algorithms are slashing the cost of fixing Flints water crisis

Michigan researchers, including the Michigan Data Science student team, are using new algorithmic and statistical tools to help inform crisis response in Flint. Profs. Jacob Abernethy and Eric Schwartz of the Business School explain how in this article at the Conversation. [Full Story]

Related Topics:  Abernethy, Jake  Artificial Intelligence  Big Data  Lab-Artificial Intelligence  Student Teams and Organizations  

Hacking Healthcare - How Big Data is Driving Big Changes in Medicine

The article by CoE writer Gabe Cherry highlights the work being done by Jenna Wiens and her collaborators on using big data to predict which hospital patients are at risk of developing a life-threatening intestinal infection called Clostridium difficile, or C. diff. It also provides context on the big data initiatives taking at UM in general and with respect to healthcare, and across EECS, including work by Prof. Barzan Mozafari on how to improve the design of big data databases. [Full Story]

Related Topics:  Baveja, Satinder Singh  Big Data  Hero, Alfred  Lab-Artificial Intelligence  Machine Learning  Michielssen, Eric  Mower Provost, Emily  Mozafari, Barzan  Wiens, Jenna  

Correlation is Not Causation: Electrical Analysis of St. Jude Implant Shows Normal Pacing

This blog post by the Archimedes Center for Medical Device Security provides additional technical detail regarding the claims by Muddy Waters and St. Jude regarding pacemaker/defibrillator security. Prof. Kevin Fu, who heads the Archimedes Center, and his collaborators at Michigan have concluded that those claims are questionable. [Full Story]

Related Topics:  Fu, Kevin  Lab-Computer Engineering (CE Lab)  Security (Computing)  

Holes Found in Report on St. Jude Medical Device Security

Michigan researchers including Prof. Kevin Fu have reproduced experiments alleging security flaws in St. Jude Medical's pacemakers and other life-saving medical devices and have concluded that those claims are questionable. The report alleging the security flaws was released last week by short-selling investment research firm Muddy Waters Capital LLC and medical device security firm MedSec Ltd. [Full Story]

Related Topics:  Fu, Kevin  Lab-Computer Engineering (CE Lab)  Security (Computing)  

Several Michigan Papers Presented at 2016 USENIX Security Symposium

Five papers authored by CSE researchers were presented at the 2016 USENIX Security Symposium, which took place August 10-12 in Austin, TX, and two papers were presented at WOOT 2016. USENIX Security brings together researchers from both academia and industry interested in the latest advances in the security of computer systems and networks. The symposium is a premier venue for security and privacy research. [Full Story]

Related Topics:  Halderman, J. Alex  Lab-Software Systems  Prakash, Atul  Shin, Kang G.  

Researchers David Adrian and Prof. J. Alex Halderman Receive Pwnie Award for Work on DROWN Attack

A research team that includes CSE PhD student David Adrian and Prof. J. Alex Halderman has been awarded the Pwnie Award for Best Cryptographic Attack at the Black Hat conference for their work on the DROWN attack. DROWN allows attackers to break encryption used to protect HTTPS websites and read or steal sensitive communications, including passwords, credit card numbers, trade secrets, or financial data. [Full Story]

Related Topics:  Graduate Students  Halderman, J. Alex  Lab-Software Systems  Security (Computing)  

CSE-Based Startup Receives Funding to Develop Systems Based on Intelligent Personal Assistant Technology

Artificial Intelligence startup Clinc, founded by Profs. Jason Mars and Lingjia Tang along with Research Fellow Michael Laurenzano and CSE graduate student Johann Hauswald, is off and running in downtown Ann Arbor. On August 4, 2016, the company announced a $225,000 National Science Foundation Grant and closure of a $1.2 million round of seed funding. [Full Story]

Related Topics:  Artificial Intelligence  Lab-Artificial Intelligence  Lab-Computer Engineering (CE Lab)  Mars, Jason  Tang, Lingjia  

Researchers Seek to Help the Disabled with Intelligent Robotic Wheelchair

Prof. Ben Kuipers, CSE graduate student Collin Johnson, and researcher Dr. Jong Jin Park have created Vulcan, an intelligent robotic wheelchair. Vulcan learns the spatial structure of the environment it moves through and it uses that knowledge to plan and follow routes from place to place. Robotic wheelchairs will benefit people who need a wheelchair, but are unable to use one because of multiple disabilities. [Full Story]

Related Topics:  Kuipers, Benjamin  Lab-Artificial Intelligence  

With Over 7 Million Certificates Issued, Let's Encrypt Aims to Secure the Entire Web

Let's Encrypt, the non-profit certificate authority founded by Prof. J. Alex Halderman with colleagues at Mozilla and Electronic Frontier Foundation, is well on its way to securing the web. By making the switch to HTTPS free and easy, Let's Encrypt has issued over 7 million certificates since December 2015. [Full Story]

Related Topics:  Digital Democracy  Halderman, J. Alex  Lab-Software Systems  Networking, Operating Systems, and Distributed Systems  Security (national and personal safety)  

New Venture is on the Path to Build Continual Learning AIs

Cogitai, Inc., a continual learning company co-founded by Prof. Satinder Singh Baveja, is developing AI technology that empowers machines to learn from interaction with the real world, enabling everyday things that sense and act to get smarter, more skilled, and more knowledgeable with experience. The company has recently announced funding by Sony. [Full Story]

Related Topics:  Artificial Intelligence  Baveja, Satinder Singh  Lab-Artificial Intelligence  

Data Equality on the Internet Might Bring Unintended Consequences

Prof. Harsha Madhyastha was interviewed on Michigan Radio about the possibilities for unintended consequences of net neutrality, and the difficulty of finding an acceptable alternative. [Full Story]

Related Topics:  Lab-Software Systems  Madhyastha, Harsha  Networking, Operating Systems, and Distributed Systems  

Can Slower Financial Traders Find a Haven in a World of High-Speed Algorithms?

In this article at The Conversation, Prof. Michael Wellman reviews the latency arms race at the center of high-speed algorithmic trading, in which the first trader to react is able to make money off of slower rivals. He describes the possibility for a frequent call market, in which speed no longer categorically prevails, and how it could be implemented. [Full Story]

Related Topics:  Artificial Intelligence  Lab-Artificial Intelligence  Wenisch, Thomas  

Tracking and Mitigating Tail Latency in Data Centers

Computer science researchers have developed a modular load tester platform for data centers which is designed to help measure and mitigate tail latency. Called Treadmill, it is described in their paper, "Treadmill: Attributing the Source of Tail Latency through Precise Load Testing and Statistical Inference." [Full Story]

Related Topics:  Alumni  Artificial Intelligence  Big Data  Computer Architecture  Graduate Students  Lab-Artificial Intelligence  Lab-Computer Engineering (CE Lab)  Mars, Jason  Tang, Lingjia  

Two Michigan Papers Win Top Awards at IEEE Security and Privacy Symposium

Two papers authored by EECS researchers were selected for top honors at the 37th IEEE Symposium on Security and Privacy. One of the papers, describing and demonstrating a malicious hardware backdoor, received the Distinguished Paper Award. The second, which demonstrated security failings in a commercial smart home platform, received the Distinguished Practical Paper Award. [Full Story]

Related Topics:  Austin, Todd  Computer Architecture  Graduate Students  Hicks, Matt  Internet of Things  Lab-Computer Engineering (CE Lab)  Lab-Software Systems  Prakash, Atul  Security (Computing)  Sylvester, Dennis  

Proxy Optimizes Webpage Loading for Better User Experience

Researchers led by Prof. Harsha V. Madhyastha have developed a new web proxy called Klotski, which seeks to improve users' perceptions of how quickly a webpage loads on a mobile device by maximizing the amount of important content on the page that is fetched and displayed within the users attention span. [Full Story]

Related Topics:  Lab-Software Systems  Madhyastha, Harsha  Networking, Operating Systems, and Distributed Systems  

Patented Camera Calibration Tool Automates Calibration Target Acquisition

Prof. Edwin Olson and two of his former students, Johannes Strom and Andrew Richardson, have recently been awarded a United States Patent for their work in the development of AprilCal, an interactive camera calibration tool that automates the challenging task of calibration image acquisition. [Full Story]

Related Topics:  Computer Vision  Lab-Artificial Intelligence  Olson, Edwin  

Collecting Data to Better Identify Bipolar Disorder

Prof. Emily Mower Provost is collaborating with researchers at the University of Michigan Depression Center to develop new technologies that provide individuals and their caregivers with insight into how bipolar disorder changes over time. [Full Story]

Related Topics:  Artificial Intelligence  Lab-Artificial Intelligence  Mower Provost, Emily  Women in Computing  

Rada Mihalcea Leads Research Team to Develop Analytics for Learners as People

Prof. Rada Mihalcea has received funding from the Michigan Institute for Data Science (MIDAS) to uncover connections between personal attributes and success or well-being. The multidisciplinary research team includes Profs. Satinder Singh Baveja and Emily Mower Provost from CSE. [Full Story]

Related Topics:  Big Data  Lab-Artificial Intelligence  Mihalcea, Rada  Women in Computing  

CSE Faculty Amongst Researchers in Three of Four Funded MIDAS Projects

The Michigan Institute for Data Science (MIDAS) has funded four projects for $1.25M each in the first round of its Challenge Initiatives program, which is designed to fund extraordinary projects with major social impact. Prof. Rada Mihalcea is leading one of the projects, which seeks to uncover connections between personal attributes and success or well-being; overall, a number of CSE faculty are amongst the investigators in three of the four projects. [Full Story]

Related Topics:  Big Data  Engineering for the Greater Good  Lab-Artificial Intelligence  Mihalcea, Rada  

Two Papers by Michigan Researchers Chosen as IEEE Micro Top Picks

Two papers authored by EECS researchers have been selected for IEEE Micro's Top Picks from the 2015 Computer Architecture Conferences. The two papers from Michigan introduced the Sirius personal digital assistant and the MBus bus for modular microcomputing systems. [Full Story]

Related Topics:  Blaauw, David  Computer Architecture  Dreslinski, Ron  Dutta, Prabal  Graduate Students  Lab-Computer Engineering (CE Lab)  Mars, Jason  Mudge, Trevor  Tang, Lingjia  

U-M researchers work to determine when people are lying

This article reports on work being done by Prof. Rada Mihalcea and Prof. Mihai Burzo (UM Flint), who have built unique lie-detecting software based on real-world data. Their prototype considers both a speaker's words and gestures, and unlike a polygraph, it doesn't need to touch the subject in order to work. [Full Story]

Related Topics:  Computational Linguistics  Lab-Artificial Intelligence  Mihalcea, Rada  Women in Computing  

The AI Machines Undergoing Behavioral Psychology Tests

As reported in MIT Technology Review, graduate student researchers Junhyuk Oh and Valliappa Chockalingam, along with Profs. Satinder Singh Baveja and Honglak Lee have created mazes in Minecraft to perform reinforcement learning experiments on artificial intelligence entities. [Full Story]

Related Topics:  Artificial Intelligence  Baveja, Satinder Singh  Graduate Students  Lab-Artificial Intelligence  Lee, Honglak  Machine Learning  

David Chesney Awarded Funding to Research Treatment for Traumatic Brain Injury

A team of researchers, including Dr. David Chesney and co-PI Dr. Rodney C. Daniels (Pediatric Critical Care) received funding for their research proposal at the Massey Foundation Traumatic Brain injury (TBI) Grand Challenge Pitch Day, which took place April 29th. Their research proposal was one of five U-M research proposals that were selected to receive funding. [Full Story]

Related Topics:  Chesney, David  Technology and Wellness  

This "Demonically Clever" Backdoor Hides in a Tiny Slice of a Computer Chip

This article in Wired describes work by Michigan researchers that demonstrates how a hacker could hide a malicious backdoor in silicon and trigger it to gain access to a computing system. Google engineer Yonatan Zunger is quoted as saying "This is the most demonically clever computer security attack Ive seen in years." [Full Story]

Related Topics:  Austin, Todd  Blaauw, David  Computer Architecture  Graduate Students  Lab-Computer Engineering (CE Lab)  Security (Computing)  

Show All