東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Ransomware Detection with XGBoost Ha...

Gajjar, Archit,

FindBook

Google Book

Amazon

博客來

Ransomware Detection with XGBoost Hardware Acceleration for Data Centers Using High-Level Synthesis /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Ransomware Detection with XGBoost Hardware Acceleration for Data Centers Using High-Level Synthesis // Archit Gajjar.
作者:	Gajjar, Archit,
面頁冊數:	1 electronic resource (91 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
標題:	Operating systems. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615832
ISBN:	9798380483704

Ransomware Detection with XGBoost Hardware Acceleration for Data Centers Using High-Level Synthesis /
Gajjar, Archit,

Ransomware Detection with XGBoost Hardware Acceleration for Data Centers Using High-Level Synthesis /Archit Gajjar. - 1 electronic resource (91 pages)

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Over the last decade, the cybersecurity community observed a surge in cybersecurity attacks, especially ransomware due to its notoriously costly and turbulent impact on the public as well as private sectors. Ransomware remains one of the most threatening cybersecurity attacks due to its relatively easy-to-practice nature. Tremendous efforts have been spent on developing techniques to detect ransomware to, ideally, protect the data or have as minimum data loss as possible.In order to detect ransomware, the Machine Learning (ML) approach has proven to be more effective compared to classical signature-based detection. Moreover, decision tree-based algorithms such as Random Forest (RF), Decision Trees (DT), eXtreme Gradient Boosting (XGBoost), Classification And Regression Tree (CART), spike up interest among cybersecurity researchers. Due to the nature of the problem, traditional CPUs and GPUs falter to keep up with the desired performance, especially for a large data workload. Thus, the problem demands a customized solution that can swiftly detect the ransomware and sustain the data center workload.We employ XGBoost, one of the prominent ML algorithms, to design an accelerator to address the ransomware detection problem. Ransomware attacks are becoming more frequent and sophisticated as there is a constant tussle between attackers and cybersecurity defenders. Hence, the solution markets ML models to be efficient and readily deployable. We propose a customized FPGA accelerator to address the problem from multiple angles. Typically, a design with Hardware Description Language (HDL) approach takes relatively longer to define the architecture and verify it before it can be operated. So, we propose an emerging High-Level Synthesis (HLS)-based approach to designing custom FPGA hardware that improves design and verification time compared to HDL designs. The use of HLS makes updating the ML model process seamless to face the new zero-day ransomware. Moreover, we show the capability to approach the problem from more than one type of set of features boosting the confidence of the model to have robust predictions by looking at Hardware Performance Counters (HPCs), Operating System (OS) calls, and network traffic information simultaneously.

English

ISBN: 9798380483704Subjects--Topical Terms:

3681934
Operating systems.

Ransomware Detection with XGBoost Hardware Acceleration for Data Centers Using High-Level Synthesis /
LDR:03659nmm a22004093i 4500 001 2430332
005 20250519115943.5
006 m o d
007 cr|nu||||||||
008 261011s2023 miu||||||m |||||||eng d
020 $a 9798380483704
035 $a (MiAaPQD)AAI30615832
035 $a (MiAaPQD)NCState_Univ18402040998
035 $a AAI30615832
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Gajjar, Archit, $e author. $3 3818598
245 1 0 $a Ransomware Detection with XGBoost Hardware Acceleration for Data Centers Using High-Level Synthesis / $c Archit Gajjar.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (91 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisors: Franzon, Paul D. Committee members: Davis, Rhett; Aysu, Aydin; Yu, Ruozhou.
502 $b Ph.D. $c North Carolina State University $d 2023.
520 $a Over the last decade, the cybersecurity community observed a surge in cybersecurity attacks, especially ransomware due to its notoriously costly and turbulent impact on the public as well as private sectors. Ransomware remains one of the most threatening cybersecurity attacks due to its relatively easy-to-practice nature. Tremendous efforts have been spent on developing techniques to detect ransomware to, ideally, protect the data or have as minimum data loss as possible.In order to detect ransomware, the Machine Learning (ML) approach has proven to be more effective compared to classical signature-based detection. Moreover, decision tree-based algorithms such as Random Forest (RF), Decision Trees (DT), eXtreme Gradient Boosting (XGBoost), Classification And Regression Tree (CART), spike up interest among cybersecurity researchers. Due to the nature of the problem, traditional CPUs and GPUs falter to keep up with the desired performance, especially for a large data workload. Thus, the problem demands a customized solution that can swiftly detect the ransomware and sustain the data center workload.We employ XGBoost, one of the prominent ML algorithms, to design an accelerator to address the ransomware detection problem. Ransomware attacks are becoming more frequent and sophisticated as there is a constant tussle between attackers and cybersecurity defenders. Hence, the solution markets ML models to be efficient and readily deployable. We propose a customized FPGA accelerator to address the problem from multiple angles. Typically, a design with Hardware Description Language (HDL) approach takes relatively longer to define the architecture and verify it before it can be operated. So, we propose an emerging High-Level Synthesis (HLS)-based approach to designing custom FPGA hardware that improves design and verification time compared to HDL designs. The use of HLS makes updating the ML model process seamless to face the new zero-day ransomware. Moreover, we show the capability to approach the problem from more than one type of set of features boosting the confidence of the model to have robust predictions by looking at Hardware Performance Counters (HPCs), Operating System (OS) calls, and network traffic information simultaneously.
546 $a English
590 $a School code: 0155
650 4 $a Operating systems. $3 3681934
650 4 $a Behavior. $3 532476
650 4 $a Software. $2 gtt. $3 619355
650 4 $a Data integrity. $3 2142314
650 4 $a Data processing. $3 680224
650 4 $a Design. $3 518875
650 4 $a Data encryption. $3 3680528
650 4 $a Batch processing. $3 3680543
650 4 $a Energy consumption. $3 631630
650 4 $a Linux. $3 738943
650 4 $a Computer science. $3 523869
650 4 $a Energy. $3 876794
650 4 $a Information technology. $3 532993
650 4 $a Web studies. $3 2122754
690 $a 0389
690 $a 0984
690 $a 0791
690 $a 0489
690 $a 0646
710 2 $a North Carolina State University. $e degree granting institution. $3 3765716
720 1 $a Franzon, Paul D. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-04B.
790 $a 0155
791 $a Ph.D.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615832