CSE
CSE
CSE CSE

CSE Research News

Advancing AI for video

Prof. Jason Corso's startup launches powerful video processing platform. [Full Story]

Related Topics:  Artificial Intelligence  Autonomous Vehicles  Corso, Jason  Entrepreneurship and Tech Transfer  Machine Learning  

Researchers use Rowhammer bit flips to steal 2048-bit crypto key

Researchers including Prof. Daniel Genkin have unveiled a new attack that lets unprivileged attackers corrupt or change data stored in vulnerable memory chips. This attack, called RAMBleed, can allow third parties access cryptographic keys or other secrets stored in vulnerable DRAM modules. [Full Story]

Related Topics:  Cybersecurity  Genkin, Daniel  Graduate Students  Lab-Systems  

A quicker eye for robotics to help in our cluttered, human environments

In a step toward home-helper robots that can quickly navigate unpredictable and disordered spaces, University of Michigan researchers have developed an algorithm that lets machines perceive their environments orders of magnitude faster than similar previous approaches. [Full Story]

Related Topics:  Artificial Intelligence  Assistive Technology  Computer Vision  Graduate Students  Jenkins, Chad  Lab-Artificial Intelligence  

3D Modeling Representations, David Fouhey, TRI and a Cat

Prof. David Fouhey wants your computer to be as smart as your cat. Now, he has funding from Toyota Research Institute to fund his research into computer vision. [Full Story]

Related Topics:  Computer Vision  Fouhey, David  Lab-Artificial Intelligence  

New chip stops hacks before they start

A new computer processor architecture developed at the University of Michigan could usher in a future where computers proactively defend against threats, rendering the current electronic security model of bugs and patches obsolete. [Full Story]

Related Topics:  Austin, Todd  Computer Architecture  Cybersecurity  Lab-Computer Engineering (CE Lab)  

Chowdhury receives VMWare Award to further research on cluster-wide memory efficiency

Prof. Mosharaf Chowdhury has been awarded the VMWare Early Career Award to further his research on memory disaggregation. The award provides a $50,000 unrestricted gift for his work, which seeks to one day treat portions of computer memory scattered across machines as one huge, virtual block of memory. [Full Story]

Related Topics:  Chowdhury, Mosharaf  Computer Architecture  Lab-Systems  Warehouse-Scale and Parallel Systems  

Award for helping popular websites better direct their internet traffic

A paper co-authored by Prof. Harsha Madhyastha has been awarded an Applied Networking Research Prize by the Internet Engineering Task Force (IETF). In Engineering Egress with Edge Fabric: Steering Oceans of Content to the World, Madhyastha and collaborators presented a system that large content providers can use to smartly direct traffic over the internet to their users. [Full Story]

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

All things are part of the Internet of Things with new RFID system

Frying pans, pill bottles, yoga mats, coffee cups, and countless other non-electronic objects could be turned into a network of Internet of Things sensors with a new RFID-based technology from Prof. Alanson Sample. [Full Story]

Related Topics:  Embedded Systems  Internet of Things  Lab-Computer Engineering (CE Lab)  Sample, Alanson  

New secure architecture confounds hackers with randomization

Prof. Todd Austin is leading development of a new hardware architecture designed to guard against hackers. The two lead PhD students on the project, Mark Gallagher and Lauren Biernacki, produced a promotional video detailing the strengths of Morpheus' randomization approach. [Full Story]

Related Topics:  Austin, Todd  Computer Architecture  Cybersecurity  Graduate Students  

Two solutions for GPU efficiency can boost AI performance

GPUs are employed by large computing clusters for both training and inference of deep learning models, and Prof. Mosharaf Chowdhury and his students, Juncheng Gu and Peifeng Yu, are working to multiply the number of jobs a cluster can finish in a set amount of time and streamline methods of sharing resources on the fly with two new open-source tools. [Full Story]

Related Topics:  Chowdhury, Mosharaf  Graduate Students  Lab-Systems  Machine Learning  Warehouse-Scale and Parallel Systems  

Personalized knowledge graphs for faster search and digital assistants

Prof. Danai Koutra has proposed a mobile solution to develop constantly-evolving, personalized knowledge bases that identify information thats most relevant to the users changing interests. Koutra and her collaborators are working to take on this shortcoming with graphs that are customized, stored locally, and able to change over time. Koutra earned an Amazon Research Award for the project. [Full Story]

Related Topics:  Big Data  Koutra, Danai  Lab-Interactive Systems  Mobile Computing  

Election security: Halderman recommends actions to ensure integrity of US systems

Prof. J. Alex Halderman testified in front of the US House Appropriations Subcommittee on Financial Service and General Government, urging lawmakers to approve additional funding for election cybersecurity prior to the upcoming 2020 elections. [Full Story]

Related Topics:  Cybersecurity  Halderman, J. Alex  Lab-Systems  

"Air traffic control" for driverless cars could speed up deployment

Research led by Prof. Walter Lasecki shows how human-generated responses could remotely assist autonomous vehicles decisions during times of uncertainty. [Full Story]

Related Topics:  Artificial Intelligence  Autonomous Vehicles  Data and Computing  Lab-Artificial Intelligence  Lab-Interactive Systems  Lasecki, Walter  

Built by humans. Ruled by computers.

H.V. Jagadish, the Bernard A. Galler Collegiate Professor of Electrical Engineering and Computer Science at U-M, has been tapped to lead the Center for Responsible Information Technology, a U-M think tank thats now in development. It will aim to help technologists use algorithmic systems and other IT advances in a socially responsible way. [Full Story]

Related Topics:  Artificial Intelligence  Cybersecurity  Jagadish, HV  Koutra, Danai  Lab-Artificial Intelligence  Lab-Interactive Systems  

Online censorship detector aims to make the internet a freer place

In an advance that could one day provide a comprehensive, publicly available window into worldwide internet censorship, a team led by Prof. Roya Ensafi has turned public internet servers across the globe into automated sentries that can monitor and report when access to websites is being blocked. [Full Story]

Related Topics:  Cybersecurity  Ensafi, Roya  Lab-Systems  

Bridging the "last centimeter barrier" in electronic communications

Michigan Engineering researchers led by Prof. Pinaki Mazumder have created a new chip interconnect technology using terahertz surface-wave interconnects that will enable ultra fast data transmissions. [Full Story]

Related Topics:  Computer Architecture  Lab-Computer Engineering (CE Lab)  Mazumder, Pinaki  

Taking on the limits of computing power

By harnessing the power and speed of graphics processing units, a University of Michigan startup can dramatically accelerate gene sequencing, shortening tasks that took multiple days to a single hour. Ann Arbor-based Parabricks Inc. was recently awarded a National Science Foundation Small Business Innovation Research Phase II grant of $748,000.

[Full Story]

Related Topics:  Entrepreneurship and Tech Transfer  Health and Safety  Lab-Computer Engineering (CE Lab)  Mahlke, Scott  

Helping drivers use smart cars smarter

Profs. Jason Mars, Lingja Tang, CSE students Shih-Chieh Lin, Chang-Hong Hsu, and Yunqi Zhang, and Ford Motor Company have developed a conversational in-vehicle digital assistant that can respond to drivers questions and commands in natural language, helping them get to know the autonomous tools their cars have to offer. Their paper earned Honorable Mention Award in the Best Paper competition at this years ACM User Interface Software and Technology Symposium (UIST). [Full Story]

Related Topics:  Automotive industry  Autonomous Vehicles  Graduate Students  Lab-Artificial Intelligence  Mars, Jason  Tang, Lingjia  

Using drones, a new software tool can bring LTE networks anywhere

Prof. Z. Morley Mao and alumnus Mehrdad Moradi (PhD CSE 2018) earned a best paper award at this year's ACM MobiCom for their work on SkyCore, a reliable new way to deploy LTE networks using unmanned aerial vehicles (UAVs). The paper, SkyCore: Moving Core to the Edge for Untethered and Reliable UAV-based LTE networks, demonstrated a way to connect hotspots on drones with commercial networks and smartphones. [Full Story]

Related Topics:  Autonomous Vehicles  Lab-Systems  Mao, Zhuoqing Morley  Mobile Computing  

403 Forbidden Study reveals new data on region-specific website blocking practices

New work led by Prof. Roya Ensafi and PhD student Allison McDonald undertook the first wide-scale measurement study of server-side geographic restrictions, or geoblocking, a phenomenon in which websites block access for users in particular countries or regions, a phenomenon on the rise causing Internet balkanization. [Full Story]

Related Topics:  Ensafi, Roya  Graduate Students  Information Technology  Lab-Systems  

Two papers announced among 10 most influential in healthcare and infection control

Prof. Jenna Wiens group had two papers highlighted in a session on the top 10 most influential papers in healthcare epidemiology and infection control at Infectious Disease Week (IDWeek 2018). The papers were selected for their impact, the number of times they were cited in the preceding two years, and their potential effect on future research and technology. [Full Story]

Related Topics:  Health and Safety  Lab-Artificial Intelligence  Machine Learning  Wiens, Jenna  

The logic of feeling: Teaching computers to identify emotions

Using machine learning to decode the unpredictable world of human emotion might seem like an unusual choice. But in the ambiguity of human expression, U-M computer science and engineering associate professor Emily Mower Provost has discovered a rich trove of data waiting to be analyzed. [Full Story]

Related Topics:  Artificial Intelligence  Health and Safety  Lab-Artificial Intelligence  Machine Learning  Mower Provost, Emily  

Making software failures a little less catastrophic

Prof. Baris Kasikci presented a new technique called REPT REverse debugging with Processor Trace. In the paper REPT: Reverse Debugging of Failures in Deployed Software, Kasikci and collaborators propose a method to recreate the failing program execution to better diagnose the problem at hand. This technique is now deployed on Windows systems and the Windows Debugger platform. [Full Story]

Related Topics:  Kasikci, Baris  Lab-Systems  Software Systems  

Gaining a deeper understanding of how personal values are expressed in text

Content analysis of large collections of text is often a useful first step in understanding what people are talking or writing about. PhD student Steve Wilson, Prof. Rada Mihalcea, and Master student Yiting Shen have proposed a new method of performing these analyses in their paper, Building and Validating Hierarchical Lexicons with a Case Study on Personal Values. The researchers earned a Best Paper Award at the 2018 International Conference on Social Informatics (SocInfo) for their work. [Full Story]

Related Topics:  Graduate Students  Lab-Artificial Intelligence  Language and Text Processing  Mihalcea, Rada  Women in Computing  

Tyche: A new permission model to defend against smart home hacks

Prof. Atul Prakash, CSE PhD student Kevin Eykholt, and CSE alumni Amir Rahmati and Earlence Fernandes have proposed Tyche, a safer app permissions system for smart homes and the Internet of Things. Their paper on this project, Tyche: A Risk-Based Permission Model for Smart Homes, received a Best Paper Award at the IEEE Cybersecurity Development Conference. [Full Story]

Related Topics:  Alumni  Cybersecurity  Graduate Students  Internet of Things  Lab-Systems  Prakash, Atul  

Detecting Huntington's disease with an algorithm that analyzes speech

In an advance that could one day provide new insight into the progression of neurological diseases like Huntington's disease, Alzheimers and Parkinson's, researchers including Prof. Emily Mower Provost have demonstrated the first automated system that uses speech analysis to detect Huntington's disease. [Full Story]

Related Topics:  Big Data  Health and Safety  Lab-Artificial Intelligence  Machine Learning  Mower Provost, Emily  

Fake news detector algorithm works better than a human

An algorithm-based system that identifies telltale linguistic cues in fake news stories could provide news aggregator and social media sites like Google News with a new weapon in the fight against misinformation. Led by Prof. Rada Mihalcea, the researchers have demonstrated that its comparable to and sometimes better than humans at correctly identifying fake news stories. [Full Story]

Related Topics:  Artificial Intelligence  Big Data  Communications  Lab-Artificial Intelligence  Mihalcea, Rada  

Making online communication smarter with Trove Video

Trove is an Ann-Arbor based artificial intelligence startup built on the vision of improving communication using artificial intelligence. Profs. Danai Koutra and Walter Lasecki are collaborating with the company to develop novel methods and tools that will help make intelligent online communication smarter. [Full Story]

Related Topics:  Big Data  Communications  Koutra, Danai  Lab-Artificial Intelligence  Lasecki, Walter  

Intel processor vulnerability could put millions of PCs at risk

A newly discovered processor vulnerability could potentially put secure information at risk in any Intel-based PC manufactured since 2008. It could affect users who rely on a digital lockbox feature known as Intel Software Guard Extensions, or SGX, as well as those who utilize common cloud-based services. CSE researchers contributed to the discovery of the security hole, called Foreshadow. [Full Story]

Related Topics:  Cybersecurity  Genkin, Daniel  Graduate Students  Kasikci, Baris  Lab-Systems  Wenisch, Thomas  

Using software to beat Moore's Law: $9.5M to design the reconfigurable computer

In search of a new way to overcome the limitations of silicon, Prof. Ron Dreslinski is leading a project with a $9.5million DARPA grant to develop a hardware architecture and software ecosystem that together can approach the power of ASICs with the flexibility of a CPU. Called Transmuter, this software-defined hardware can change how programs use the hardware available to them in real time, effectively acting as a reconfigurable computer. [Full Story]

Related Topics:  Computer Architecture  Dreslinski, Ron  Integrated Circuits and VLSI  

Enabling anyone to design hardware with a new open-source tool

In a $6.5 million U-M-led project that could revolutionize and democratize designing hardware devices, Professors Wentzloff, Blaauw, Dreslinski, and Sylvester will work to create an open-source hardware compiler that aims to reduce the six month process of hand-designing analog circuits to a dramatically faster and automated 24-hour routine. [Full Story]

Related Topics:  Blaauw, David  Computer-Aided Design & VLSI  Dreslinski, Ron  Integrated Circuits and VLSI  Lab-Michigan Integrated Circuits (MICL)  Sylvester, Dennis  Wentzloff, David  

Michigan chips will be first to test next-generation hardware design tools

Professors Sylvester, Blaauw, and Dreslinski will test tools and provide feedback in a national program that aims to build free, open-source electronic design automation tools. [Full Story]

Related Topics:  Blaauw, David  Computer-Aided Design & VLSI  Dreslinski, Ron  Integrated Circuits and VLSI  Lab-Michigan Integrated Circuits (MICL)  Sylvester, Dennis  

Tool for structuring data creates efficiency for data scientists

Transforming messy data into a usable state turns out to be labor-intensive and tedious. Traditionally, domain experts handwrite task-specific scripts to transform unstructured data. Enter Foofah, a project developed by CSE graduate students Zhongjun Jin and Michael Anderson, Prof. Michael Cafarella, and Bernard A. Galler Collegiate Professor of Electrical Engineering and Computer Science H.V. Jagadish that can help to minimize the effort and required background knowledge needed to clean up data. [Full Story]

Related Topics:  Big Data  Cafarella, Michael  Data and Computing  Graduate Students  Jagadish, HV  

Undocumented immigrants' privacy at risk online, on phones

Every day, undocumented immigrants in the U.S. face discrimination, surveillance, deportation, and other dangers. When it comes to their smartphones, immigrants struggle to apply instinctive caution, according to a study by a team of University of Michigan researchers that included CSE PhD student Allison McDonald. [Full Story]

Related Topics:  Cybersecurity  Graduate Students  Halderman, J. Alex  

Cafarella Receives VLDB Test of Time Award for Structured Web Data Search

This award is given to the VLDB paper published ten years earlier that has had the most influence since its publication. In this paper, Cafarella and co-authors Alon Halevy, Zhe Daisy Wang, Eugene Wu, and Yang Zhang set out to determine how to provide search-engine-style access to huge volumes of structured web data. [Full Story]

Related Topics:  Big Data  Cafarella, Michael  Data and Computing  

Designing a flexible future for massive data centers

The days of bulky, expensive servers filling up data centers may be numbered: a new approach recreates the power of a large server by linking up and pooling the resources of smaller computers with fast networking technology. [Full Story]

Related Topics:  Big Data  Chowdhury, Mosharaf  Lab-Systems  Mozafari, Barzan  Networking, Operating Systems, and Distributed Systems  

Study maps careers of CS PhDs using decades of data

Of the many burning questions in the world of computing research, the one most dear to a student's heart has typically been the least investigated: what happens after a PhD in computer science? Prof. Danai Koutra and CSE PhD student Tara Safavi set out to provide the world's first data-driven answer, analyzing several decades of post-PhD computing careers using a large new dataset rich with professional information. [Full Story]

Related Topics:  Big Data  Data and Computing  Koutra, Danai  

"Stitching" together a web user from scattered, messy data

Modern internet users submit a massive trove of personal details to the web - but they scatter their data across dozens of websites, accounts, and devices with very little continuity. Prof. Danai Koutra will work to "stitch" these personal details together into a cohesive, useful whole, making a user's time online a more pleasant, continuous experience across devices with better product and service recommendations. [Full Story]

Related Topics:  Big Data  Data and Computing  Koutra, Danai  

Building a security standard for a post-quantum future

Chris Peikert, with a team of eleven other researchers, has submitted a cryptographic scheme as a proposed standard to the NIST Post-Quantum Cryptography project. Called FrodoKEM, this family of encryption algorithms is designed to be a conservative and practical implementation of one of the most-studied approaches in the post-quantum cryptography field. [Full Story]

Related Topics:  Cybersecurity  Peikert, Chris  Quantum Science and Technology  

$6.25M project will decode worlds most complex networks

A new $6.25 million project built on game theory and led by Professors Mingyan Liu and Michael Wellman will develop tools to understand and shape online and on-the-ground networks that drive human decision making. [Full Story]

Related Topics:  Liu, Mingyan  Networking, Operating Systems, and Distributed Systems  Wellman, Michael  

CSE researchers win Best of SELSE award

have won the the best paper award at the 14th Workshop on Silicon Errors in Logic - System Effects (SELSE) for their paper entitled "Low Cost Transient Fault Protection Using Loop Output Prediction." [Full Story]

Related Topics:  Alumni  Computer Architecture  Graduate Students  Lab-Computer Engineering (CE Lab)  Mahlke, Scott  

Preventing deadly hospital infections with machine learning

New machine learning models tailored to individual hospitals could give them a much earlier prediction of which patients are most likely to develop C. difficile, potentially helping them stave off infection before it starts. The models are detailed in a paper published today in Infection Control and Hospital Epidemiology. [Full Story]

Related Topics:  Lab-Artificial Intelligence  Wiens, Jenna  

Michigan researchers discover vulnerabilities in next-generation connected vehicle technology

The US Department of Transportation has started implementing I-SIG, a vehicle-to-infrastructure technology that uses real-time vehicle trajectory data to intelligently control the duration and sequence of traffic signals. With the use of this system, comes vulnerabilities, and Michigan researchers have demonstrated that even one single cyberattack can greatly manipulate the intelligent traffic control algorithm in the current I-SIG system and cause severe traffic jams. [Full Story]

Related Topics:  Lab-Systems  Mao, Zhuoqing Morley  

Cuba "sonic attacks" - a covert accident?

The purported "sonic attacks" that sickened U.S. and Canadian government workers in Cuba last year could have been an accidental side effect of attempted eavesdropping, says Prof. Kevin Fu, who with his colleagues reverse-engineered the attacks in a lab. [Full Story]

Related Topics:  Cybersecurity  Embedded Systems  Fu, Kevin  Lab-Computer Engineering (CE Lab)  

New computing system to enable deep space missions

A new radiation-hardened, multi-processor, Arm-based spacecraft processor is being developed at Michigan in a project led by Boeing and funded by NASA. Prof. Ron Dreslinski is leading the research at Michigan. [Full Story]

Related Topics:  Computer Architecture  Dreslinski, Ron  Lab-Computer Engineering (CE Lab)  Mudge, Trevor  

Chat tool simplifies tricky online privacy policies

Kang G. Shin, the Kevin and Nancy O'Connor Professor of Computer Science, and his collaborators have created an automated chatbot that uses artificial intelligence to weed through the fine print of privacy policies so that you will know what you're agreeing to. [Full Story]

Related Topics:  Artificial Intelligence  Lab-Artificial Intelligence  Shin, Kang G.  

Michigan researchers predict emotions by examining the correlation between tweets and environmental factors

Research fellow Carmen Banea, alumna Vicki Liu, and Prof. Rada Mihalcea explored the concept of grounded emotions, focusing on how external factors, ranging from weather, news exposure, social network emotion charge, timing, and mood predisposition may have a bearing on ones emotion level throughout the day. [Full Story]

Related Topics:  Lab-Artificial Intelligence  Language and Text Processing  Mihalcea, Rada  

Internet-scanning U-M startup pioneers new approach to cybersecurity

Ann Arbor-based Censys has launched based on work done over the past 5 years in Prof. J. Alex Halderman's lab. Censys is the first commercially available internet-wide scanning tool. It helps IT experts working to secure large networks, which are composed of a constantly changing array of devices ranging from servers to smartphones and internet-of-things devices. [Full Story]

Related Topics:  Cybersecurity  Halderman, J. Alex  Lab-Systems  

Reimagining how computers are designed: University of Michigan leads new $32M center

The Center for Applications Driving Architectures, or ADA, at the University of Michigan will develop a transformative, "plug-and-play" ecosystem to encourage a flood of fresh ideas in computing frontiers such as autonomous control, robotics and machine-learning. [Full Story]

Related Topics:  Bertacco, Valeria  Computer Architecture  Lab-Computer Engineering (CE Lab)  

U-M startup May Mobility blazes toward autonomous fleet market

May Mobility, co-founded and led by Prof. Edwin Olson, has tested its autonomous vehicles on the streets of Downtown Detroit. The startup recently licensed five autonomous driving related technologies from U-M, and outside of the life sciences, is the most successful UM startup in raising first round of funding so quickly. [Full Story]

Related Topics:  Autonomous Vehicles  Lab-Artificial Intelligence  Olson, Edwin  Robotics and Autonomous Systems  

Show All