소장자료

>>
소장자료
>
000 nam5i
001 2210080934304
003 DE-He213
005 20250321105353
007 cr nn 008mamaa
008 240603s2024 si | s |||| 0|eng d
020 a97898197042559978-981-97-0425-5
024 a10.1007/978-981-97-0425-52doi
040 a221008
050 aQ334-342
050 aTA347.A78
072 aUYQ2bicssc
072 aCOM0040002bisacsh
072 aUYQ2thema
082 a006.3223
100 aChen, Jinyin.eauthor.4aut4http://id.loc.gov/vocabulary/relators/aut
245 00 aAttacks, Defenses and Testing for Deep Learningh[electronic resource] /cby Jinyin Chen, Ximin Zhang, Haibin Zheng.
250 a1st ed. 2024.
264 aSingapore :bSpringer Nature Singapore :bImprint: Springer,c2024.
300 aXX, 399 p. 128 illus., 126 illus. in color.bonline resource.
336 atextbtxt2rdacontent
337 acomputerbc2rdamedia
338 aonline resourcebcr2rdacarrier
347 atext filebPDF2rda
505 aPerturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm -- Feature Transfer Based Stealthy Poisoning Attack for DNNs -- Adversarial Attacks on GNN Based Vertical Federated Learning -- A Novel DNN Object Contour Attack on Image Recognition -- Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning -- Targeted Label Adversarial Attack on Graph Embedding -- Backdoor Attack on Dynamic Link Prediction -- Attention Mechanism based Adversarial Attack against DRL -- Characterizing Adversarial Examples via Local Gradient Checking -- A Novel Adversarial Defense by Refocusing on Critical Areas -- Neuron-level Inverse Perturbation Against Adversarial Attacks -- Adaptive Channel Transformation-based Detector for Adversarial Attacks -- Defense Against Free-rider Attack From the Weight Evolving Frequency -- An Effective Model Copyright Protection for Federated Learning -- Guard the vertical federated graph learning from Property Inference Attack -- Using Adversarial Examples to Against Backdoor Attack in FL -- Evaluating the Adversarial Robustness of Deep Model by Decision Boundaries -- Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space -- Interpretable White-Box Fairness Testing through Biased Neuron Identification -- A Deep Learning Framework for Dynamic Network Link Prediction. .
520 aThis book provides a systematic study on the security of deep learning. With its powerful learning ability, deep learning is widely used in CV, FL, GNN, RL, and other scenarios. However, during the process of application, researchers have revealed that deep learning is vulnerable to malicious attacks, which will lead to unpredictable consequences. Take autonomous driving as an example, there were more than 12 serious autonomous driving accidents in the world in 2018, including Uber, Tesla and other high technological enterprises. Drawing on the reviewed literature, we need to discover vulnerabilities in deep learning through attacks, reinforce its defense, and test model performance to ensure its robustness. Attacks can be divided into adversarial attacks and poisoning attacks. Adversarial attacks occur during the model testing phase, where the attacker obtains adversarial examples by adding small perturbations. Poisoning attacks occur during the model training phase, where the attacker injects poisoned examples into the training dataset, embedding a backdoor trigger in the trained deep learning model. An effective defense method is an important guarantee for the application of deep learning. The existing defense methods are divided into three types, including the data modification defense method, model modification defense method, and network add-on method. The data modification defense method performs adversarial defense by fine-tuning the input data. The model modification defense method adjusts the model framework to achieve the effect of defending against attacks. The network add-on method prevents the adversarial examples by training the adversarial example detector. Testing deep neural networks is an effective method to measure the security and robustness of deep learning models. Through test evaluation, security vulnerabilities and weaknesses in deep neural networks can be identified. By identifying and fixing these vulnerabilities, the security and robustness of the model can be improved. Our audience includes researchers in the field of deep learning security, as well as software development engineers specializing in deep learning.
650 aArtificial intelligence.
650 aComputer engineering.
650 aComputer networks .
650 aNeural networks (Computer science) .
650 aArtificial Intelligence.
650 aComputer Engineering and Networks.
650 aMathematical Models of Cognitive Processes and Neural Networks.
700 aZhang, Ximin.eauthor.4aut4http://id.loc.gov/vocabulary/relators/aut
700 aZheng, Haibin.eauthor.4aut4http://id.loc.gov/vocabulary/relators/aut
710 aSpringerLink (Online service)
773 tSpringer Nature eBook
776 iPrinted edition:z9789819704248
776 iPrinted edition:z9789819704262
776 iPrinted edition:z9789819704279
856 uhttps://doi.org/10.1007/978-981-97-0425-5
912 aZDB-2-SCS
912 aZDB-2-SXCS
950 aComputer Science (SpringerNature-11645)
950 aComputer Science (R0) (SpringerNature-43710)
Attacks, Defenses and Testing for Deep Learning[electronic resource] /by Jinyin Chen, Ximin Zhang, Haibin Zheng
종류
전자책
서명
Attacks, Defenses and Testing for Deep Learning[electronic resource] /by Jinyin Chen, Ximin Zhang, Haibin Zheng
저자명
판 사항
1st ed. 2024.
형태사항
XX, 399 p 128 illus, 126 illus in color online resource.
주기사항
This book provides a systematic study on the security of deep learning. With its powerful learning ability, deep learning is widely used in CV, FL, GNN, RL, and other scenarios. However, during the process of application, researchers have revealed that deep learning is vulnerable to malicious attacks, which will lead to unpredictable consequences. Take autonomous driving as an example, there were more than 12 serious autonomous driving accidents in the world in 2018, including Uber, Tesla and other high technological enterprises. Drawing on the reviewed literature, we need to discover vulnerabilities in deep learning through attacks, reinforce its defense, and test model performance to ensure its robustness. Attacks can be divided into adversarial attacks and poisoning attacks. Adversarial attacks occur during the model testing phase, where the attacker obtains adversarial examples by adding small perturbations. Poisoning attacks occur during the model training phase, where the attacker injects poisoned examples into the training dataset, embedding a backdoor trigger in the trained deep learning model. An effective defense method is an important guarantee for the application of deep learning. The existing defense methods are divided into three types, including the data modification defense method, model modification defense method, and network add-on method. The data modification defense method performs adversarial defense by fine-tuning the input data. The model modification defense method adjusts the model framework to achieve the effect of defending against attacks. The network add-on method prevents the adversarial examples by training the adversarial example detector. Testing deep neural networks is an effective method to measure the security and robustness of deep learning models. Through test evaluation, security vulnerabilities and weaknesses in deep neural networks can be identified. By identifying and fixing these vulnerabilities, the security and robustness of the model can be improved. Our audience includes researchers in the field of deep learning security, as well as software development engineers specializing in deep learning.
관련 URL

소장정보

도서예약
서가부재도서 신고
보존서고신청
캠퍼스대출
우선정리신청
검색지인쇄
등록번호 청구기호 별치기호 소장위치 대출상태 반납예정일 서비스
전자자료는 소장사항이 존재하지 않습니다

책소개

전체 메뉴 보기