Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Shi, Wenchang"'
Autor:
Si, Meixue, Pan, Shidong, Liao, Dianshu, Sun, Xiaoyu, Tao, Zhen, Shi, Wenchang, Xing, Zhenchang
The rapid development and widespread adoption of Generative Artificial Intelligence-based (GAI) applications have greatly enriched our daily lives, benefiting people by enhancing creativity, personalizing experiences, improving accessibility, and fos
Externí odkaz:
http://arxiv.org/abs/2407.15407
Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches
Autor:
Feng, Jianan, Li, Jiachun, Miao, Changqing, Huang, Jianjun, You, Wei, Shi, Wenchang, Liang, Bin
Object detection has found extensive applications in various tasks, but it is also susceptible to adversarial patch attacks. Existing defense methods often necessitate modifications to the target model or result in unacceptable time overhead. In this
Externí odkaz:
http://arxiv.org/abs/2311.06122
Autor:
Jiang, Erya, Qin, Bo, Wang, Qin, Wu, Qianhong, Li, Sanxi, Shi, Wenchang, Bi, Yingxin, Tang, Wenyi
Publikováno v:
International Conference on Information and Communications Security, pp. 645-664. Singapore: Springer Nature Singapore, 2023
Trading data through blockchain platforms is hard to achieve \textit{fair exchange}. Reasons come from two folds: Firstly, guaranteeing fairness between sellers and consumers is a challenging task as the deception of any participating parties is risk
Externí odkaz:
http://arxiv.org/abs/2211.10001
Autor:
Yu, Dongsong, Yang, Guangliang, Meng, Guozhu, Gong, Xiaorui, Zhang, Xiu, Xiang, Xiaobo, Wang, Xiaoyu, Jiang, Yue, Chen, Kai, Zou, Wei, Lee, Wenke, Shi, Wenchang
To investigate the status quo of SEAndroid policy customization, we propose SEPAL, a universal tool to automatically retrieve and examine the customized policy rules. SEPAL applies the NLP technique and employs and trains a wide&deep model to quickly
Externí odkaz:
http://arxiv.org/abs/2102.09764
Publikováno v:
Jisuanji kexue, Vol 50, Iss 4, Pp 277-287 (2023)
Vulnerabilities in third-party libraries are widely propagated to host applications(software that using third-party libra-ries),and developers of host applications usually fail to fix these vulnerabilities in a timely manner,which easily leads to sec
Externí odkaz:
https://doaj.org/article/4fb0be9b2e8e4dfe85e380e01492a564
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Computers & Security January 2023 124
Publikováno v:
In Computers & Security November 2022 122
Publikováno v:
In Computer Networks 4 August 2022 213
Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense techniques were p
Externí odkaz:
http://arxiv.org/abs/1705.08378