Hardware accelerated authentication system for dynamic time-critical networks

Ankush Singla, Purdue University


The secure and efficient operation of time-critical networks, such as vehicular networks, smart-grid and other smart-infrastructures, is of primary importance in today’s society. It is crucial to minimize the impact of security mechanisms over such networks so that the safe and reliable operations of time-critical systems are not being interfered. ^ Even though there are several security mechanisms, their application to smart-infrastructure and Internet of Things (IoT) deployments may not meet the ubiquitous and time-sensitive needs of these systems. That is, existing security mechanisms either introduce a significant computation and communication overhead, or they are not scalable for a large number of IoT components. In particular, as a primary authentication mechanism, existing digital signatures cannot meet the real-time processing requirements of time-critical networks, and also do not fully benefit from advancements in the underlying hardware/software of IoTs. ^ As a part of this thesis, we create a reliable and scalable authentication system to ensure secure and reliable operation of dynamic time-critical networks like vehicular networks through hardware acceleration. The system is implemented on System-On-Chips (SoC) leveraging the parallel processing capabilities of the embedded Graphical Processing Units (GPUs) along with the CPUs (Central Processing Units). We identify a set of cryptographic authentication mechanisms, which consist of operations that are highly parallelizable while still maintain high standards of security and are also secure against various malicious adversaries. We also focus on creating a fully functional prototype of the system which we call a “Dynamic Scheduler” which will take care of scheduling the messages for signing or verification on the basis of their priority level and the number of messages currently in the system, so as to derive maximum throughput or minimum latency from the system, whatever the requirement may be.^




Elisa Bertino, Purdue University, Ioannis Papapanagiotou, Purdue University.

Subject Area

Computer science

Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server