Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/520022
Title: | Deep learning techniques for privacy preserving cyber security in the industrial internet of things paradigm |
Researcher: | Radha, D |
Guide(s): | Kavitha, M G |
Keywords: | Computer Science Computer Science Information Systems Cyber security Deep learning Engineering and Technology Industrial internet of things |
University: | Anna University |
Completed Date: | 2023 |
Abstract: | At present, there is an urgent need for globally competitive newlineproducts with more variability, better as well as dependable quality, reduced newlinecost, and shorter life cycles. The espousal of the Internet of Things (IoT) in newlineindustrial applications leverages communication between people, data newlineanalytics, and smart machines to meet the new demands in the market while newlinecontinuing to realize their business goals. Industrial Internet, also known as newlinethe Industrial Internet of Things (IIoT) optimizes production schedules, newlinecoordinates industrial processes, enhances operational efficiency and newlineproductivity, reduces asset downtime and cost, and minimizes human error in newlineseveral industries such as aerospace, automobile, agriculture, healthcare, newlinetransportation, energy, etc. The IIoT networks contain smart sensors, actuators, instruments, newlineembedded software, and distributed communication networks to collect, newlineprocess, analyze, and communicate a huge volume of data. The privacysensitive newlineand security-critical telemetry data in IIoT networks make them newlinetempting targets for cyberattacks where malicious agents can easily gain newlineaccess to insecure IIoT devices. The IIoT network is characterized by rigorous newlinetimeliness constraints and functions with solemn security and/or financial loss newlineimplications in the event of a security breach. An intrusion detection system newline(IDS) is an indispensable cog that has been widely used in IIoT networks to newlinerecognize malevolent network activities. IDS models sense malevolent newlineinstances and create a salubrious environment for business. newlineNumerous prevailing computing models integrate distributed and newlinecoordinated services using artificial intelligence (AI) methods (e. g., newlinealgorithms for data and text mining, machine learning (ML), deep learning newline(DL), etc.), communication technology, and data science for designing newline cybersecurity tools. Even though DL-based IDSs perform better in identifying newlinenew cyberattacks they are frequently hampered by some restrictions including newlinehigher false alarm rates, deprived reliability, ineffectiv |
Pagination: | xvii,205p. |
URI: | http://hdl.handle.net/10603/520022 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 26.12 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 3.04 MB | Adobe PDF | View/Open | |
03_content.pdf | 229.56 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 271.88 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 824.69 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 433.9 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 1.76 MB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 5.39 MB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 4.66 MB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 3.41 MB | Adobe PDF | View/Open | |
11_annexures.pdf | 102.37 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 98.06 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: