國立虎尾科技大學 |

Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial Attack.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial Attack./
作者:	Gupta, Kishor Datta.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	169 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
Contained By:	Dissertations Abstracts International83-02B.
標題:	Noise. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28650214
ISBN:	9798535510415

Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial Attack.
Gupta, Kishor Datta.

Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial Attack. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 169 p.

Source: Dissertations Abstracts International, Volume: 83-02, Section: B.

Thesis (Ph.D.)--The University of Memphis, 2021.

This item must not be sold to any third party vendors.

Defenses against adversarial attacks are essential to ensure the reliability of machine learning models as their applications are expanding in different domains. Existing ML defense techniques have several limitations in practical use. I proposed a trustworthy framework that employs an adaptive strategy to inspect both inputs and decisions. In particular, data streams are examined by a series of diverse filters before sending to the learning system and then crossed checked its output through a diverse set of filters before making the final decision. My experimental results illustrated that the proposed active learning-based defense strategy could mitigate adaptive or advanced adversarial manipulations both in input and after with the model decision for a wide range of ML attacks by higher accuracy. Moreover, the output decision boundary inspection using a classification technique automatically reaffirms the reliability and increases the trustworthiness of any ML-Based decision support system. Unlike other defense strategies, my defense technique does not require adversarial sample generation, and updating the decision boundary for detection makes the defense systems robust to traditional adaptive attacks.

ISBN: 9798535510415Subjects--Topical Terms:

671314
Noise.
Subjects--Index Terms:

Adversarial machine learning

Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial Attack.
LDR:02417nam a2200385 4500 001 1067224
005 20220823142321.5
008 221020s2021 ||||||||||||||||| ||eng d
020 $a 9798535510415
035 $a (MiAaPQ)AAI28650214
035 $a AAI28650214
040 $a MiAaPQ $c MiAaPQ
100 1 $a Gupta, Kishor Datta. $3 1182296
245 1 0 $a Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial Attack.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 169 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
500 $a Advisor: Dasgupta, Dipankar.
502 $a Thesis (Ph.D.)--The University of Memphis, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Defenses against adversarial attacks are essential to ensure the reliability of machine learning models as their applications are expanding in different domains. Existing ML defense techniques have several limitations in practical use. I proposed a trustworthy framework that employs an adaptive strategy to inspect both inputs and decisions. In particular, data streams are examined by a series of diverse filters before sending to the learning system and then crossed checked its output through a diverse set of filters before making the final decision. My experimental results illustrated that the proposed active learning-based defense strategy could mitigate adaptive or advanced adversarial manipulations both in input and after with the model decision for a wide range of ML attacks by higher accuracy. Moreover, the output decision boundary inspection using a classification technique automatically reaffirms the reliability and increases the trustworthiness of any ML-Based decision support system. Unlike other defense strategies, my defense technique does not require adversarial sample generation, and updating the decision boundary for detection makes the defense systems robust to traditional adaptive attacks.
590 $a School code: 1194.
650 4 $a Noise. $3 671314
650 4 $a Neural networks. $3 1011215
650 4 $a Genetic algorithms. $3 655041
650 4 $a Datasets. $3 1372549
650 4 $a Information science. $3 561178
650 4 $a Information technology. $3 559429
650 4 $a Artificial intelligence. $3 559380
650 4 $a Applied mathematics. $3 1069907
650 4 $a Computer engineering. $3 569006
650 4 $a Computer science. $3 573171
653 $a Adversarial machine learning
653 $a Bio-inspired algorithm
653 $a Negative selection
690 $a 0984
690 $a 0489
690 $a 0464
690 $a 0800
690 $a 0723
690 $a 0364
710 2 $a The University of Memphis. $b Computer Science. $3 1372684
773 0 $t Dissertations Abstracts International $g 83-02B.
790 $a 1194
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28650214