This is an umbrella project for various topics around advanced hardware in relation to the Linux kernel, in progress at Boston University under the direction of Ulrich Drepper. The projects are: Investigate Cache and Memory Bandwidth Limitation Support in Xeon Processors Processor Extension to Predict Future States Tuning Kernel Network Parameters With Reinforcement Learning
February 27, 2019
Unikernels offer some very interesting advantages to application deployers and users, particularly in a container or even serverless context where there may be no need for an application to have a divide between user space and kernel space. Until now however unikernels have been built from scratch in research settings, which generally means they lack things like device driver support that the Linux ecosystem takes for granted. This project takes on the challenge of using Linux as a unikernel. The goal is to support deploying userlevel applications as unikernels by simply changing make CC=gcc to make CC=ukl-gcc where ukl-gcc is […]
INRIA – On-Demand/Programmable VIMs’ Collaborations to Operate and Use Geo-Distributed Infrastructures
The objective is to improve management aspects of edge-clouds and facilitate deployment and adoption through a common software platform that will offer well-adopted cloud computing capabilities. • OpenStack based • Two directions • Make OpenStack WANwide deployment a reality • Design a domain specific language to enable on-demand/ programmable collaborations between remote VIMs docs.google.com/document/d/1GK9dZTL8UIxBmMa5DdFO6ZXe9dfW2nuB_WLTB6cmtek/edit?usp=sharing Taiga RIG Inventory project here
February 26, 2019
ECHO – Edge-Cloud: Holistic Optimization and Autonomous Management of Distributed Applications and Resources
Edge-Cloud: Holistic Optimization and Autonomous Management of Distributed Applications and Resources The proposal is about optimizing the infrastructure usage and applications placement based on information provided by the applications (like through service mesh/istio) and the monitorization operators (like prometheus), but not only including local cluster, but multicluster of different sizes/types. Taiga RIG Inventory project here
Deliver an infrastructure management system for the holistic management of computing, storage and networking resources, encompassing techniques for runtime adaptations of all BigDataStack operations bigdatastack.eu Taiga RIG Inventory project here
Taiga RIG Inventory project here
STARKs are a promising new direction for zero-knowledge proofs. It is currently being commercialized for an application in cryptocurrencies, yet the approach is very attractive in general to solve a number of generic privacy-related challenges, albeit it comes at significant computational costs. What is needed at its core is very often the proof of knowledge of a preimage of an output of a hash function without revealing said preimage. Currently used hash functions are not at all designed for this purpose, and we expect that with custom designs overall protocol performance can be spend up by more than an order […]
PSI protocols have been studied for over a decade already. A recent work in our group is to see how much private-contact discovery, a special-case of private-set intersection (PSI), can be sped up such that it can scale to global use-cases. The result is that we have identified two protocols based on MPC, and proposed efficient instantiations and implementations of them for mobile environments that are up to 1000x faster than the previously best approaches. This leads already to acceptable runtimes even if server-sets contain hundreds of millions of contacts, one-time setup data transfers are still prohibitive for popular use […]
This is a project proposal combining the expertise of the crypto group with the expertise of the group of Daniel Gruss. Various approaches to prevent microarchitectural attacks can benefit from data/address scrambling schemes. One example is the recent introduction of the cipher Qarma by ARM to enforce code-flow integrity. The goal of this project is to apply such approaches to many more potential cases for countering any kind of microarchitectural side-channel attacks. For this, it is necessary to do the following for every such case: (1) Study which concrete requirements for the scrambling scheme can be deduced. This includes differential […]
Branch prediction and store-to-load-forwarding are clearly not the only “optimistic” techniques in processors. We want to investigate all “optimistic” techniques across various processors (Intel, AMD, ARM, IBM, Apple, etc.) to find the next Spectre as early as possible. Any mechanism performing an operation not explicitly requested by the instruction stream must be analyzed for possible leakage. We are already working in this direction and would be happy to intensify our efforts here. Taiga RIG Inventory project link here
Taiga RIG Inventory project here
After many different works on Rowhammer the current situation is largely unclear: The prevalence numbers we have on DDR3 say 60-80% of modules are affected. What is the prevalence of DDR4? Has Rowhammer become a niche problem? With ECC and TRR bypassable in practice – which countermeasures should high-availability systems employ to minimize risks? A systematization will provide a thorough overview and answer these questions. Taiga RIG Inventory project here
Develop a DSL to support describing textile creation in a unified, open way Taiga RIG Inventory project here
Fingerprinting database workloads with optimal tuning and then applying that tuning to other matching fingerprints Taiga RIG Inventory project here
We aim to design and implement an enterprise grade Partitioning Hypervisor using lessons from the industry and academia. Partitioning Hypervisors are intended for usecases where performance and security are critical for end-users and complex systems can be partitioned and handed over to guest OSes that can manage these partitions with minimal interaction with the hypervisor. A secure communication channel between the running guests enables the host system to behave as a distributed system. (Internal link to the project description below). Link to Details: http://file.rdu.redhat.com/~bdas/research_proposal_v2.txt Taiga RIG Inventory project here
Sponsored by: TACR (Technology Agency of Czech Republic) Partners: Honeywell, Brno University of Technology, Masaryk University, Brno – Honeywell as main recipient and project leader, the rest, including RH are partners. Start date: January 2019 End date: December 2021 Responsible person for Red Hat: Kamil Dudka (firstname.lastname@example.org) The Automation of Formal Verification (AUFOVER) project responds to the ever-growing need for rapid and high-quality software verification that is carried out within the development lifecycle. In the recent years, the university partners of the project have developed, on the basis of formal mathematical methods, an innovative way of verification, which the industrial […]
Sponsored by: TACR (Technology Agency of Czech Republic) Partners: Faculty of Business, Brno University of Technology – Red Hat as industrial partner Start date: January 2019 End date: December 2021 Responsible person for Red Hat: Matej Hrusovsky (email@example.com) – for the time being. Technical information on the project can be found here: iscorecard.org/project-background Taiga RIG Inventory project here
Sponsored by: TACR (Technology Agency of Czech Republic) Partners: FEE CTU (Faculty of Electrical Engineering, Czech Technical University), Red Hat as industrial partner. Start date: January 2017 End date: December 2020 Responsible person for Red Hat: Stefan Bunciak (firstname.lastname@example.org) The main goal of the project is to design, implement and verify a framework for quality assurance of products based on the Internet of Things (IoT) concept. The aim of the framework is to help individual IoT projects to establish an efficient testing and verification strategy of the infrastructure. Efficient quality assurance decreases project and product risks as well as the […]
The Open Source and Inclusion Project aims to identify metrics for measuring the inclusivity of Open Source Project/Communities. Initial focus is working on NLP-based solutions based on commit messages, mailing list archives, and similar — more methods will follow. Taiga RIG Inventory project here
ChRIS is an open source framework to democratize medical analytics application development in the cloud. It allows medical image processing researchers to write codes that can plug into an OpenShift-based framework that handles retrieving the data to operate on and then displaying (if appropriate) the result of the processing. More details here; Taiga RIG Inventory project here.
The purpose of this major project is to create a self-sustaining at-scale public cloud based on the Open Cloud eXchange model. It will serve as a marketplace for industry partners as well as a place for researchers and industry to innovate and expose innovation to real users. See massopen.cloud for more details. See Taiga RIG Inventory project here.
STILL is a research lab located in the Department of Computer Science, Faculty of Electrical Engineering, Czech Technical University in Prague dedicated to research in software testing and search based software engineering. The overall aim of the lab is to develop new tools and strategies for testing complex software systems in efficient and automated way. The lab also aims to help industrial partners for developing cost-effective and advanced testing techniques for real-world systems.
July 16, 2018
VeriFIT is a group including researchers and students from FIT BUT interested in research on methods of automated analysis and verification of systems. The interests of the group include formal analysis and verification (static analysis, abstract interpretation, model checking), dynamic analysis (i.e., analysis at run-time), intelligent testing as well as methods of self-healing of systems. The group is involved in basic research in the described areas as well as in development and evaluation of prototype verification tools.
October 30, 2017
The laboratory aims at intensifying the basic and applied research in the area of parallel and distributed methods for the specification, modeling, analysis, and verification of parallel and distributed systems. The mainspring of the research is the development and application of theories which underlie mentioned system development activities. The objective is to bridge the gap between academics and industry by exploiting academically well-founded formal methods and by promoting theory formation in the academic sense on the major issues of selected industrial areas. We want to come-up with practical solutions and tooling to address the needs found in current and innovative […]
Centre for Research on Cryptography and Security enables both graduate and pre-graduate students to gain practical experience with current security and crypto solutions and technologies. The main areas of interest are user and data authentication, secure usage of smartcards, security for Internet of Things, usable security. More specific areas of interest are selected with respect to current developments and in accordance with senior members’ current research focus – for an overview of current research projects/areas see this link.
October 26, 2017