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

FindBook

Google Book

Amazon

博客來

Adversary Aware Continual Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Adversary Aware Continual Learning./
作者:	Umer, Muhammad.
面頁冊數:	1 online resource (129 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
Contained By:	Dissertations Abstracts International84-12A.
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30525471click for full text (PQDT)
ISBN:	9798379693831

Adversary Aware Continual Learning.
Umer, Muhammad.

Adversary Aware Continual Learning. - 1 online resource (129 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: A.

Thesis (Ph.D.)--Rowan University, 2023.

Includes bibliographical references

Continual learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, these approaches are adversary agnostic, i.e., they do not consider the possibility of malicious attacks. In this dissertation, we have demonstrated that continual learning approaches are extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation to the model in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific class at test time. We then propose a novel defensive framework to counter such an insidious attack where, we use the attacker's primary strength - hiding the back-door pattern by making it imperceptible to humans - against it and propose to learn a perceptible (stronger) pattern (also during the training) that can overpower the attacker's imperceptible (weaker) pattern. We demonstrate the effectiveness of the proposed defensive mechanism through various commonly used replay-based (both generative and exact replay-based) continual learning algorithms using CIFAR-10, CIFAR-100, and MNIST benchmark datasets. Most noteworthy, we show that our proposed defensive framework considerably improves the robustness of continual learning algorithms with ZERO knowledge of the attacker's target task, attacker's target class, shape, size, and location of the attacker's pattern. The proposed defensive framework also does not depend on the underlying continual learning algorithm. We term our proposed defensive framework as Adversary Aware Continual Learning (AACL).

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379693831Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

Continual learning approachesIndex Terms--Genre/Form:

542853
Electronic books.

Adversary Aware Continual Learning.
LDR:03043nmm a2200409K 4500 001 2364838
005 20231212064433.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379693831
035 $a (MiAaPQ)AAI30525471
035 $a AAI30525471
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Umer, Muhammad. $3 3705659
245 1 0 $a Adversary Aware Continual Learning.
264 0 $c 2023
300 $a 1 online resource (129 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: 84-12, Section: A.
500 $a Advisor: Polikar, Robi.
502 $a Thesis (Ph.D.)--Rowan University, 2023.
504 $a Includes bibliographical references
520 $a Continual learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, these approaches are adversary agnostic, i.e., they do not consider the possibility of malicious attacks. In this dissertation, we have demonstrated that continual learning approaches are extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation to the model in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific class at test time. We then propose a novel defensive framework to counter such an insidious attack where, we use the attacker's primary strength - hiding the back-door pattern by making it imperceptible to humans - against it and propose to learn a perceptible (stronger) pattern (also during the training) that can overpower the attacker's imperceptible (weaker) pattern. We demonstrate the effectiveness of the proposed defensive mechanism through various commonly used replay-based (both generative and exact replay-based) continual learning algorithms using CIFAR-10, CIFAR-100, and MNIST benchmark datasets. Most noteworthy, we show that our proposed defensive framework considerably improves the robustness of continual learning algorithms with ZERO knowledge of the attacker's target task, attacker's target class, shape, size, and location of the attacker's pattern. The proposed defensive framework also does not depend on the underlying continual learning algorithm. We term our proposed defensive framework as Adversary Aware Continual Learning (AACL).
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer engineering. $3 621879
650 4 $a Continuing education. $3 527504
653 $a Continual learning approaches
653 $a AACL
653 $a MNIST benchmark
653 $a Backdoor pattern
653 $a Insidious attack
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0544
690 $a 0800
690 $a 0651
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Rowan University. $b Electrical and Computer Engineering. $3 3353098
773 0 $t Dissertations Abstracts International $g 84-12A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30525471 $z click for full text (PQDT)