Blar i NTNU Open på forfatter "Petrovic, Slobodan"
-
A machine learning approach to detecting malware in TLS traffic using resilient network features
Jenseg, Odin (Master thesis, 2019)The growth of malware utilizing encrypted channels makes it challenging to detect malicious activity using current Network Intrusion Detection Systems (NIDSs). The current network intrusion detection systems utilize pattern ... -
A method for approximate matching in intrusion detection systems using an extended bit-parallel algorithm
Arnason, Adrian Haveraaen (Master thesis, 2020)Flere av dagens innbruddsdeteksjonssystemer baserer seg på eksakt mønstergjenkjenning for å oppdage trusler. Algoritmer som Aho-Corasick er foretrukne siden de prosesserer flere mønstre om gangen, noe som gjør dem i stand ... -
A Study of Applied Passive TLS Analysis
Torbjørnsen, Anders Sefjord (Master thesis, 2018)While the Internet is moving towards more and more encryption of the network traffic, it is also a trend that is picked up by authors of malware. The traditional way of detecting malicious traffic or malicious behaviour ... -
Advancing Neuro-Fuzzy Algorithm for Automated Classification in Largescale Forensic and Cybercrime Investigations: Adaptive Machine Learning for Big Data Forensic
Shalaginov, Andrii (Doctoral theses at NTNU;2018:57, Doctoral thesis, 2018)Abstract Cyber Crime Investigators are challenged by the huge amount and complexity of digital data seized in criminal cases. Human experts are present in the Court of Law and make decisions with respect to the digital ... -
Analyzing Digital Evidence Using Parallel k-means with Triangle Inequality on Spark
Chitrakar, Ambika Shrestha; Petrovic, Slobodan (Chapter; Peer reviewed, 2018)Analyzing digital evidence has become a big data problem, which requires faster methods to handle them on a scalable framework. Standard k-means clustering algorithm is widely used in analyzing digital evidence. However, ... -
Applying K-means with Triangle Inequality on Apache Flink, with Applications in Intrusion Detection
Ringdalen, Ola Flølo (Master thesis, 2020)K-means er en av de mest brukte kluster-algoritmene, men den fungerer på en relativt naiv måte og majoriteten av distansekalkulasjonene den utfører er unødvendige. Tidligere forskning har bevist at ved å utnytte triangelaksiomet ... -
Approximate search with constraints on indels with application in SPAM filtering
Chitrakar, Ambika Shrestha; Petrovic, Slobodan (Journal article; Peer reviewed, 2015)Finding distorted occurrences of search pattern(s) in the search string by applying constraints on elementary edit operations (indels (insertions/deletions) and substitutions) is a new category of the approximate string ... -
Approximate String Matching and Filesystem Metadata Carving: A Study of Improving Precision and Recall for Assisting the Digital Forensics Backlog
Porter, Kyle (Doctoral theses at NTNU;2022:43, Doctoral thesis, 2022)The technical aspects of digital forensics are often dependent upon the progress made in other scientific fields. One such area of study whose results are often applied to digital forensics is string matching theory. String ... -
Authenticated Encryption Methods for Feedback Control Systems
Solnør, Petter (Master thesis, 2021)Tilbakekoplingssystemer krever at signaler sendes mellom sensorer, tilstandsestimatorer, regulatorer og aktuatorer. Disse signalene er sårbare for tyvlytting, som gjør at uautoriserte aktører kan få kjennskap til potensielt ... -
Collecting Network Evidence Using Constrained Approximate Search Algorithms
Chitrakar, Ambika Shrestha; Petrovic, Slobodan (Journal article; Peer reviewed, 2018)Intrusion detection systems are defensive tools that identify malicious activities in networks and hosts. In network forensics, investigators often study logs that store alerts generated by intrusion detection systems. ... -
Constrained Approximate Search Algorithms in Knowledge Discovery
Petrovic, Slobodan; Sidorova, Julia (Journal article, 2020)Knowledge discovery in big data is one of the most important applications of computing machinery today. Search is essential part of all such procedures. Search algorithms must be extremely efficient, but at the same time ... -
Cryptanalysis of a Pseudorandom Generator for Cross-Border E-Commerce
Shi, Lelai; Liu, Suhui; Petrovic, Slobodan (Journal article; Peer reviewed, 2019)In this paper, we study ciphertext-only cryptanalysis of a cascade of pseudorandom sequence generators employing linear feedback shift registers (LFSRs) with so-called irregular clocking. The cascade of LFSRs is a well-known ... -
Cryptanalysis of Irregularly Clocked LFSR: using approximate RBP search on FPGA
Øverbø, Magnus (Master thesis, 2019)Kryptoanalyse av et kryptosystem som benytter en Binary Rate Multiplier (BRM), 0/1 klokking, som nøkkelgenerator resulterer i at Siegenthaler's klassiske korrelasjonsangrep[4] ikke kan benyttes. Dette pga. at kryptoteksten ... -
Cyber-resilient Aided Inertial Navigation: Applications to Ships and Unmanned Surface Vehicles
Volden, Øystein (Doctoral theses at NTNU;2023:15, Doctoral thesis, 2023)With the recent advancement in maritime autonomy, the autonomous ship market is predicted to cut costs through more efficient operation of uncrewed ships and surface vehicles, followed by a reduction in associated construction ... -
Detecting modified network attacks through approximate matching
Kristensen, Kais (Master thesis, 2019)Deteksjon av cyberangrep ved hjelp av nettverkssensorer er svært utbredt, i den hensikt å monitorere og beskytte datanetteverk. Løsningene som benytter eksakte signaturer for å detektere ondsinnet aktivitet krever at ... -
Developing Long Short-Term Memory Mechanism and Dataset for Intrusion Detection in Critical Infrastructure by Simulation
Storeng, Jan Olaf (Master thesis, 2024)Beskyttelsen av kritisk infrastruktur er svært viktig for å kunne forsørge privatpersoner og bedrifter med essensielle ressurser. Dette kan være utfordrende grunnet det sensitive og komplekse Industrial Control System ... -
Efficient k-means Using Triangle Inequality on Spark for Cyber Security Analytics
Chitrakar, Ambika Shrestha; Petrovic, Slobodan (Chapter, 2019)With the advancement in technology and the increase in the number of digital sources, data quantity increases every day and, consequently, the cyber security related data quantity. Traditional security systems such as ... -
Efficient representation of data in intrusion detection systems
Lilja, Magnus Lien (Master thesis, 2021)Bedrifter er veldig avhengige av deres IT-systemer, som kan være store og komplekse å sikre. Nettverks-deteksjonssystemer (NIDS) brukes ofte til å overvåke sentrale punkter i nettverket og varsle administratorer når et ... -
Firewall models in cloud environments
Thingnes, Lars Gunnar (Master thesis, 2022)Denne oppgaven undersøker hvordan tradisjonelle sentraliserte og sonebaserte brannmurer kan migreres til moderne mikrosegmenterte og virtuelt distribuerte brannmurer. En slik migrering anses som en høy risiko siden den ... -
Fjernavlesning av vannmålere med LoRa-teknologi
Kristensen, Daniel B.; Barhaugen, Kevin A.; Skaue, Kristian A.; Solstad, Hans Kristian T. (Bachelor thesis, 2019)I dag blir all vannavlesning i Ringsaker kommune gjort manuelt av huseierene. Teknisk drift i Ringsaker kommune er interessert i å automatisere denne prosessen, og LoRaWAN er en teknologi som kan bli brukt for å muliggjøre ...