Show simple item record

A robust, reliable and deployable framework for In-vehicle security

dc.contributor.authorHafeez, Azeem
dc.contributor.advisorMalik, Hafiz
dc.date.accessioned2020-03-20T16:53:36Z
dc.date.availableNO_RESTRICTIONen_US
dc.date.available2020-03-20T16:53:36Z
dc.date.issued2020-04-26
dc.date.submitted2020-02-26
dc.identifier.urihttps://hdl.handle.net/2027.42/154568
dc.description.abstractCyber attacks on financial and government institutions, critical infrastructure, voting systems, businesses, modern vehicles, etc., are on the rise. Fully connected autonomous vehicles are more vulnerable than ever to hacking and data theft. This is due to the fact that the protocols used for in-vehicle communication i.e. controller area network (CAN), FlexRay, local interconnect network (LIN), etc., lack basic security features such as message authentication, which makes it vulnerable to a wide range of attacks including spoofing attacks. This research presents methods to protect the vehicle against spoofing attacks. The proposed methods exploit uniqueness in the electronic control unit electronic control unit (ECU) and the physical channel between transmitting and destination nodes for linking the received packet to the source. Impurities in the digital device, physical channel, imperfections in design, material, and length of the channel contribute to the uniqueness of artifacts. I propose novel techniques for electronic control unit (ECU) identification in this research to address security vulnerabilities of the in-vehicle communication. The reliable ECU identification has the potential to prevent spoofing attacks launched over the CAN due to the inconsideration of the message authentication. In this regard, my techniques models the ECU-specific random distortion caused by the imperfections in digital-to-analog converter digital to analog converter (DAC), and semiconductor impurities in the transmitting ECU for fingerprinting. I also model the channel-specific random distortion, impurities in the physical channel, imperfections in design, material, and length of the channel are contributing factors behind physically unclonable artifacts. The lumped element model is used to characterize channel-specific distortions. This research exploits the distortion of the device (ECU) and distortion due to the channel to identify the transmitter and hence authenticate the transmitter.en_US
dc.language.isoen_USen_US
dc.subjectIntrusion detection system (IDS)en_US
dc.subjectElectronic control unit (ECU)en_US
dc.subjectController area network (CAN)en_US
dc.subjectMachine learning (ML)en_US
dc.subjectArtificial neural network (ANN)en_US
dc.subject.otherElectrical and Computer Engineeringen_US
dc.titleA robust, reliable and deployable framework for In-vehicle securityen_US
dc.typeThesisen_US
dc.description.thesisdegreenamePhDen_US
dc.description.thesisdegreedisciplineCollege of Engineering & Computer Scienceen_US
dc.description.thesisdegreegrantorUniversity of Michigan-Dearbornen_US
dc.contributor.committeememberShaout, Adnan
dc.contributor.committeememberSelim, Awad
dc.contributor.committeememberBacha, Anys
dc.identifier.uniqname3989 8856en_US
dc.description.bitstreamurlhttps://deepblue.lib.umich.edu/bitstream/2027.42/154568/1/Azeem Hafeez Final Disseration.pdf
dc.identifier.orcid0000-0001-8855-6158en_US
dc.description.filedescriptionDescription of Azeem Hafeez Final Disseration.pdf : Dissertation
dc.identifier.name-orcidHafeez, Azeem; 0000-0001-8855-6158en_US
dc.owningcollnameDissertations and Theses (Ph.D. and Master's)


Files in this item

Show simple item record

Remediation of Harmful Language

The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.

Accessibility

If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.