Zobrazeno 1 - 10
of 808
pro vyhledávání: '"Tian Zhihong"'
Publikováno v:
中国工程科学, Vol 25, Iss 6, Pp 96-105 (2023)
The rapid development of network attack and defense technologies has posed various challenges to current cybersecurity assurance systems. Therefore, studying a new cybersecurity assurance system has become an urgent need to promote the development of
Externí odkaz:
https://doaj.org/article/b0f2b351751a42298a32a7bef52d500c
In recent years, deep learning (DL)-based methods have been widely used in code vulnerability detection. The DL-based methods typically extract structural information from source code, e.g., code structure graph, and adopt neural networks such as Gra
Externí odkaz:
http://arxiv.org/abs/2212.14274
Autor:
Hou, Yuanming, Song, Xiaocheng, Zhang, Yanqing, Ren, Tingting, Wang, Jiaxin, Qin, Jingyi, Yang, Jianjun, Xie, Zhengzheng, Tian, Zhihong, Guan, Zhongjie, Fu, Xianwei, Jiao, Shilong, Li, Qiuye, Li, Erling
Publikováno v:
In FlatChem September 2024 47
Autor:
Wang, Zhikai, Wang, Ruihua, Yuan, Huanran, Fan, Fengfeng, Li, Shaoqing, Cheng, Mingxing, Tian, Zhihong
Publikováno v:
In Gene 1 July 2024 914
With the continuous development of industrial IoT (IIoT) technology, network security is becoming more and more important. And intrusion detection is an important part of its security. However, since the amount of attack traffic is very small compare
Externí odkaz:
http://arxiv.org/abs/2110.03445
Autor:
Cong, Yue, Zeng, Yuxiang, Qiu, Jing, Fang, Zhongyang, Zhang, Lejun, Cheng, Du, Liu, Jia, Tian, Zhihong
Publikováno v:
In Knowledge-Based Systems 9 October 2024 301
Publikováno v:
In Computer Networks October 2024 252
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection methods usually
Externí odkaz:
http://arxiv.org/abs/2109.06176
Autor:
Qin, Xugong, Zhou, Yu, Guo, Youhui, Wu, Dayan, Tian, Zhihong, Jiang, Ning, Wang, Hongbin, Wang, Weiping
Due to the large success in object detection and instance segmentation, Mask R-CNN attracts great attention and is widely adopted as a strong baseline for arbitrary-shaped scene text detection and spotting. However, two issues remain to be settled. T
Externí odkaz:
http://arxiv.org/abs/2109.03426
Autor:
Tang, Keke, Miao, Dingruibo, Peng, Weilong, Wu, Jianpeng, Shi, Yawen, Gu, Zhaoquan, Tian, Zhihong, Wang, Wenping
Overconfident predictions on out-of-distribution (OOD) samples is a thorny issue for deep neural networks. The key to resolve the OOD overconfidence issue inherently is to build a subset of OOD samples and then suppress predictions on them. This pape
Externí odkaz:
http://arxiv.org/abs/2108.06024