Zobrazeno 1 - 10
of 684
pro vyhledávání: '"Backdoor attack"'
Publikováno v:
智能科学与技术学报, Vol 6, Pp 381-393 (2024)
In response to the potential risk of backdoor attacks faced by artificial intelligence systems, a range of backdoor defense strategies are developed. The diversity of the evaluation criteria for existing defense method, makes cross-method comparisons
Externí odkaz:
https://doaj.org/article/7406a82e802a4f3685b98d05f0ab4747
Publikováno v:
In Expert Systems With Applications 15 March 2025 265
Publikováno v:
In Knowledge-Based Systems 25 November 2024 304
Publikováno v:
In Expert Systems With Applications 1 April 2025 267
Publikováno v:
In Information Sciences April 2025 698
Publikováno v:
In Computers & Security March 2025 150
Publikováno v:
Tongxin xuebao, Vol 45, Pp 73-83 (2024)
Launching backdoor attacks against deep learning (DL)-based network traffic classifiers, and a method of malicious traffic escape was proposed based on the backdoor attack. Backdoors were embedded in classifiers by mixing poisoned training samples wi
Externí odkaz:
https://doaj.org/article/687444d7da334b5993d3c9455d132558
Autor:
YANG Shun, LU Hengyang
Publikováno v:
Jisuanji kexue yu tansuo, Vol 18, Iss 4, Pp 1068-1082 (2024)
Deep neural networks are susceptible to backdoor attacks during the training stage. When training an image-text retrieval model, if an attacker maliciously injects image-text pairs with a backdoor trigger into the training dataset, the backdoor will
Externí odkaz:
https://doaj.org/article/0e83e234373a4ce0a970a7cba70b4a83
Publikováno v:
Tongxin xuebao, Vol 45, Pp 182-196 (2024)
In response to the inadequacy of existing defense methods for backdoor attacks in federated learning to effectively remove embedded backdoor features from models, while simultaneously reducing the accuracy of the primary task, a federated learning ba
Externí odkaz:
https://doaj.org/article/d094649cf32244418219180584c6eb70
Publikováno v:
Applied Sciences, Vol 14, Iss 23, p 11425 (2024)
Dataset distillation has become an important technique for enhancing the efficiency of data when training machine learning models. It finds extensive applications across various fields, including computer vision (CV) and natural language processing (
Externí odkaz:
https://doaj.org/article/fee83108917d47adade7c0ec70677cd9