Research

The Spark lab's mission is to build secure systems through novel architectures with help from operating systems and compilers.

Security work today is spread across the entire stack as well as across mobile devices and cloud servers. Increasingly sensitive programs will shortly run on shiny new hardware that promise to beat Dennard-scaling hurdles but have never met a threat model. All to say, this is a good time for computer architects and systems researchers to jump in.

Spark lab's current projects build a new security-plane for distributed applications. Our projects include building a new instruction-set (ISA) and micro-architecture that translates program-layer security properties into hardware implementations, and a container-orchestrator and compiler that maps distributed web- and micro-services on to our security-ISA. For example, one series of work has been to build hardware boxes that do not leak information, and then use this to put data into boxes instead of applications.

One near-term outcome of our research is to put users back in control of their own data, even if their data is computed on by untrusted applications and infrastructure. In the long term, we'll be on Mars and leave all non-secure computers here.

Awards

  • Best Paper Nominee, HOST 2019
  • Qualcomm Faculty Award, 2018
  • Finalist, CSAW Applied Research Competition, 2018
  • Best Paper Runner-Up, HOST 2018
  • AMD Chair, Department of ECE, UT Austin, 2017-19
  • Qualcomm Faculty Award, 2017
  • Best Paper Award, ASPLOS 2015
  • NSF Career Award, January 2015
  • IEEE Micro Top Pick, Honorable Mention, January-February 2015
  • Google Faculty Research Award, 2013-14
  • Top 10 shortlist for NYU-Poly Best Applied Security Paper Award, 2013.

Publications

Group Members

Mohit Tiwari

I enjoy building new hardware-software systems that enforce well-defined security properties. Before joining UT, I received my PhD in UC Santa Barbara in 2011, and then worked as a post-doc at UC Berkeley.

Mikhail Kazdagli

My research interests span machine learning and program languages.

Team Member

Austin Harris

I am interested in designing secure processors and accelerators and prototyping them on a FPGA.

Team Member

Casen Hunger

I am interested in using machine learning and operating systems to build privacy-preserving systems.

Team Member

Rohith Prakash

I build side channel defenses and intelligent adversary models to quantify and bound theoretical information leakage.

Team Member

Ashay Rane

My research interests include compiler transformations for improving security, side-channel defenses, and public policy implications of cybersecurity.

Team Member

Aydin Aysu

I study the design, optimization, and secure implementations of next-generation cryptosystems. Before joining UT as a post-doc, I received my PhD from Virginia Tech in 2016.

Team Member

Willy Vasquez

I am interested in designing provably secure systems using cryptography and formal methods.

Team Member

Pranav Kumar

I am interested in leveraging machine learning techniques to solve security problems in architecture.

Team Member

Shijia Wei

I am interested in understanding tradeoffs between system performance and security and leveraging strengths from all layers towards a high-performance secure system.

Team Member

Prateek Sahu

My research interests lie in the domains of computer architecture, microarchitecture and security. I am eager to learn more about how hardware and software can interact to guarantee better data privacy.

Team Member