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
- Qualcomm Innovation Fellowship (North America) 2022
- Top Picks in Hardware and Embedded Security, HSTTC 2021
- 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
-
SEED'24
Tail Victims in Termination Timing Channel Defenses beyond Cryptographic Kernels
Shijia Wei, Austin Harris, Yongye Zhu, Prakash Ramrakhyani, Calvin Lin, Mohit Tiwari in Proceedings of the 2024 International Symposium on Secure and Private Execution Environment Design (SEED), May 2024, Orlando, Florida, USA. -
ICLR'24
NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
Wenxi Wang, Yang Hu, Mohit Tiwari, Sarfraz Khurshid, Ken McMillan, Risto Miikkulainen in Proceedings of the Twelfth International Conference on Learning Representations (ICLR), May 2024, Vienna, Austria. -
ASE'23
Fixing Privilege Escalations in Cloud Access Control with MaxSAT and Graph Neural Networks
Yang Hu*, Wenxi Wang*, Sarfraz Khurshid, Ken McMillan, Mohit Tiwari in Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), September 2023, Kirchberg, Luxembourg. -
USENIX'23
Rethinking System Audit Architectures for High Event Coverage and Synchronous Log Availability
Varun Gandhi*, Sarbartha Banerjee*, Aniket Agrawal, Adil Ahmad, Sangho Lee, Marcus Peinado in Proceedings of the 32nd Usenix Security Symposium (USENIX), August 2023, Anaheim, California, USA. -
ACSAC'22
Spacelord: Private and Secure Smart Space Sharing
Yechan Bae*, Sarbartha Banerjee*, Sangho Lee*, Marcus Peinado* in Proceedings of the 38th Conference on Annual Computer Security Applications (ACSAC), December 2022, Austin, Texas, USA. -
DSN'22
Back to the future: N-Versioning of Microservices
Antonio M. Espinoza, Riley Wood, Stephanie Forrest, Mohit Tiwari in Proceedings of the 52nd International Conference on Dependable Systems and Networks (DSN), June 2022, Baltimore, MD, USA. -
IJCAI/ECAI'22
Using Constraint Programming and Graph Representation Learning for Generating Interpretable Cloud Security Policies
Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar in Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), July 2022, Messe Wien, Vienna, Austria. -
HOST'21
Morpheus II: A RISC-V Security Extension for Protecting Vulnerable Software and Hardware
Austin Harris, Tarunesh Verma, Shijia Wei, Alex Kisil, Misiker Tadesse Aga, Valeria Bertacco, Baris Kasikci, Mohit Tiwari, Todd Austin in Proceedings of IEEE International Symposium on Hardware Oriented Security and Trust (HOST), December 2021, Washington D.C., USA. -
ESEC/FSE'21
ACHyb: A Hybrid Analysis Approach to Detect Kernel Access Control Vulnerabilities
Yang Hu, Wenxi Wang, Casen Hunger, Riley Wood, Sarfraz Khurshid, Mohit Tiwari, in Proceedings of the 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), August 2021, Athens, Greece. -
Arxiv'20
Sesame: Software Defined Enclaves to Secure Inference Accelerators with Multi-tenant Execution
Sarbartha Banerjee, Prakash Ramrakhyani, Shijia Wei, Mohit Tiwari Arxiv Preprint (Arxiv), July 2020. -
MICRO'19
Cyclone: Detecting Contention-Based Cache Information Leaks Through Cyclic Interference.
Austin Harris*, Shijia Wei*, Prateek Sahu, Pranav Kumar, Todd Austin, Mohit Tiwari, in Proceedings of the 52nd International Symposium on Microarchitecture (MICRO), October 2019, Columbus, OH. -
HOST'19
Using Power-Anomalies to Counter Evasive Micro-Architectural Attacks in Embedded Systems.
Shijia Wei, Aydin Aysu, Michael Orshansky, Andreas Gerstlauer, Mohit Tiwari, in Proceedings of IEEE International Symposium on Hardware Oriented Security and Trust (HOST), May 2019, Tysons Corner, USA. (Best Paper Candidate) -
ASPLOS'19
Morpheus: A Vulnerability-Tolerant Secure Architecture Based on Ensembles of Moving Target Defenses with Churn.
Mark Gallagher, Lauren Biernacki, Shibo Chen, Zelalem Birhanu Aweke, Salessawi Ferede Yitbarek, Misiker Tadesse Aga, Austin Harris, Zhixing Xu, Baris Kasikci, Valeria Bertacco, Sharad Malik, Mohit Tiwari, Todd Austin, in Proceedings of Architectural Support for Programming Languages and Operating Systems (ASPLOS), March 2019. -
ASPLOS'19
Relaxed Hierarchical ORAM.
Chandrasekhar Nagarajan, Ali Shafiee, Rajeev Balasubramonian, Mohit Tiwari, in Proceedings of Architectural Support for Programming Languages and Operating Systems (ASPLOS), March 2019. -
ASPLOS'18
DATS: Data Containers for Web Applications.
Casen Hunger, Lluis Vilanova, Charalampos Papamanthou, Yoav Etsion, Mohit Tiwari, in Proceedings of Architectural Support for Programming Languages and Operating Systems (ASPLOS), March 2018, Williamsburg, VA. -
HOST'18
Horizontal Side-Channel Vulnerabilities of Post-Quantum Key Exchange Protocols.
Aydin Aysu, Youssef Tobah, Mohit Tiwari, Andreas Gerstlauer, Michael Orshansky, in Proceedings of IEEE Internation Symposium on Hardware Oriented Security and Trust (HOST), May 2018, Washington DC, USA. (Best Paper Runner-Up) -
PETS'18 CSAW Best Applied Security Paper, Finalist
Power to peep-all: Inference Attacks by Malicious Batteries on Mobile Devices.
Pavel Lifshits, Roni Forte, Yedid Hoshen, Matthew Halpern, Manuel Philipose, Mohit Tiwari, Mark Silberstein in Journal of Privacy Enhancing Technologies Symposium -
DATE'18
Binary Ring-LWE Hardware with Power Side-Channel Countermeasures.
Aydin Aysu, Andreas Gerstlauer, Michael Orshansky, Mohit Tiwari, in Proceedings of Design Automation and Test in Europe (DATE), March 2018, Dresden, Germany. -
HPCA'18
Secure DIMM: Moving ORAM Primitives Closer to Memory.
Ali Shafiee, Rajeev Balasubramonian, Mohit Tiwari, Feifei Li, in Proceedings of High Performance Computer Architecture (HPCA), February 2018, Vienna, Austria. -
MICRO'16
Quantifying and Improving the Efficiency of Hardware-based Mobile Malware Detectors.
Mikhail Kazdagli, Vijay Janapa Reddi, Mohit Tiwari, in Proceedings of the 49th International Symposium on Microarchitecture (MICRO), October 2016, Taipei, Taiwan. -
USENIX'16
Secure, Precise, and Fast Floating-Point Operations on x86 Processors.
Ashay Rane, Calvin Lin, Mohit Tiwari, in Proceedings of the 25th Usenix Security Symposium (USENIX), August 2016, Austin, TX. -
MICRO'15
Avoiding Information Leakage in the Memory Controller with Fixed Service Policies.
Ali Shafiee, Akhila Gundu, Manjunath Shevgoor, Rajeev Balasubramonian, Mohit Tiwari, in Proceedings of the 48th International Symposium on Microarchitecture (MICRO), December 2015, Waikiki, Hawaii. -
USENIX'15
Raccoon: Closing Digital Side-Channels through Obfuscated Execution.
Ashay Rane, Calvin Lin, Mohit Tiwari, in Proceedings of the 24th Usenix Security Symposium (USENIX), August 2015, Washington D.C. Short Summary.
-
ASPLOS'15 Best Paper Award
GhostRider: A Hardware-Software System for Memory Trace Oblivious Computation.
Chang Liu, Austin Harris, Martin Maas, Michael Hicks, Mohit Tiwari, Elaine Shi, in Proceedings of the 15th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), March 2015, Istanbul, Turkey. -
HPCA'15
Understanding Contention-driven Covert Channels and Using Them for Defense.
Casen Hunger, Mikhail Kazdagli, Ankit Rawat, Alex Dimakis, Sriram Vishwanath, Mohit Tiwari, in Proceedings of the International Symposium on High Performance Computer Architecture (HPCA), February 2015. -
ASPLOS'14 IEEE Micro Top Picks, Honorable Mention, January-February 2015.
Sapper: A Language for Hardware-Level Security Policy Enforcement.
Xun Li, Vineeth Kashyap, Jason Oberg, Mohit Tiwari, Vasanth Rajarathinam, Ryan Kastner, Timothy Sherwood, Ben Hardekopf, and Frederic Chong, in Proceedings of the 14th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), March 2014, Salt Lake City. -
CCS'13 Shortlisted (top 10) for NYU-Poly AT&T Best Applied Security Paper Award, 2013
PHANTOM: Practical Oblivious Computation in a Secure Processor.
Martin Maas, Eric Love, Emil Stefanov, Mohit Tiwari, Elaine Shi, Krste Asanovic, John Kubiatowicz, Dawn Song, in Proceedings of the ACM Conference on Computer and Communications Security (CCS), November 2013, Berlin, Germany -
HASP'23
Triton: Software-Defined Threat Model for Secure Multi-Tenant ML inference Accelerators
Sarbartha Banerjee, Shijia Wei, Prakash Ramrakhyani, Mohit Tiwari in the 12th IEEE/ACM International Workshop on Hardware and Architectural Support for Security and Privacy (HASP), October 2023, Toronto, Canada. -
HotInfra'23
Sidecars on the Central Lane: Impact of Network Proxies on Microservices
Prateek Sahu, Lucy Zheng, Marco Bueso, Shijia Wei, Neeraja J. Yadwadkar, and Mohit Tiwari in Proceedings of the 2023 IEEE/ACM Workshop on Hot Topics in System Infrastructure (HotInfra), June 2023, Orlando, Florida, USA. -
SPSL'21
Bandwidth Utilization Side-Channel on ML Inference Accelerators
Sarbartha Banerjee, Shijia Wei, Prakash Ramrakhyani, Mohit Tiwari in Proceedings of the 2021 IEEE/ACM Workshop on Secure and Private Systems for Machine Learning (SPSL), April 2021, Virtual. -
HASP'14
Morpheus: Benchmarking Computational Diversity in Mobile Malware.
Mikhail Kazdagli, Ling Huang, Vijay Reddi, Mohit Tiwari in Workshop on Hardware and Architectural Support for Security and Privacy, held in conjunction with ISCA, 2014 -
HASP'14
Memory Bandwidth Reservation in the Cloud to Avoid Information Leakage in the Memory Controller.
Akhila Gundu, Gita Sreekumar, Ali Shafiee, Seth Pugsley, Hardik Jain, Rajeev Balasubramonian, Mohit Tiwari, in Workshop on Hardware and Architectural Support for Security and Privacy (HASP), held in conjunction with ISCA, 2014 -
CARL'13
A High-Performance Oblivious RAM Controller on the Convey HC-2ex Heterogeneous Computing Platform.
Martin Maas, Eric Love, Emil Stefanov, Mohit Tiwari, Elaine Shi, Krste Asanovic, John Kubiatowicz, Dawn Song, in Workshop on the Intersections of Computer Architecture and Reconfigurable Logic, 2013
Workshops
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.
Austin Harris
I am interested in designing secure processors and accelerators and prototyping them on a FPGA.
Casen Hunger
I am interested in using machine learning and operating systems to build privacy-preserving systems.
Prateek Sahu
I am interested in exploring the performance and security of modern cloud systems. I am eager to learn more about how hardware and software can interact to guarantee better data privacy.
Sarbartha Banerjee
My research interests are secure accelerators, side channel defense, machine learning security.
Mulong Luo
Mulong Luo is a postdoctoral fellow at the SPARK Lab, UT Austin. His recent research interests are machine learning for system security, and security of AI systems. He got his Ph.D. from Cornell University in 2023.
Ayush Roychowdhury
My research interests include language model security, data security, and explainable artificial intelligence for security.
Former Members
Mikhail Kazdagli
PhD 2018
Next: Essential
Aydin Aysu
Post-doc 2016-2018
Next: Assistant Professor at NC State
Rohith Prakash
MS 2018
Next: Apple
Ashay Rane
PhD 2019
Next: Groq
Pranav Kumar
MS 2019
Next: Intel
Antonio Espinoza
Post-doc 2018-2020
Next: Assistant Professor at Eastern Washington University
Riley Wood
MS 2020
Next: Apple
Yongye Zhu
B.S. 2022
Next: M.S.@UIUC
Yang Hu
PhD 2024
Next: Amazon
Shijia Wei
PhD 2024 Next: NVidia
Willy Vasquez
PhD 2024
Next: Apple