Zobrazeno 1 - 10
of 150
pro vyhledávání: '"Li, Huichen"'
Autor:
Xi, Zhe, Zhuang, Aobo, Li, Xi, Ming, Turhong Maimaiti, Cheng, Yingxue, Zhang, Chenhe, Xie, Fuan, Wang, Yue, Yan, Guangting, Zheng, Jialiang, Lin, Zhenhang, Zhang, Geng, Li, Huichen, Wu, Ting, He, Qi, Li, Wengang
Publikováno v:
In Heliyon 15 August 2024 10(15)
Autor:
Gunter, George, Li, Huichen, Hojjati, Avesta, Nice, Matthew, Bunting, Matthew, Gunter, Carl A., Li, Bo, Sprinkle, Jonathan, Work, Daniel
We demonstrate that a supply-chain level compromise of the adaptive cruise control (ACC) capability on equipped vehicles can be used to significantly degrade system level performance of current day mixed-autonomy freeway networks. Via a simple threat
Externí odkaz:
http://arxiv.org/abs/2112.11986
Boundary based blackbox attack has been recognized as practical and effective, given that an attacker only needs to access the final model prediction. However, the query efficiency of it is in general high especially for high dimensional image data.
Externí odkaz:
http://arxiv.org/abs/2106.06056
Autor:
Wang, Dong, Li, Huichen, Zeng, Tianxiang, Chen, Qiang, Huang, Weilong, Huang, Yujing, Liao, Yuqing, Jiang, Qiuhua
Publikováno v:
In Journal of Neuroimmunology 15 February 2024 387
Autor:
Chen, Qiang, Huang, Weilong, Tang, Jianhong, Ye, Guohui, Meng, Hongliang, Jiang, Qing, Ge, Linying, Li, HuiChen, Liu, Lin, Jiang, Qiuhua, Wang, Dong
Publikováno v:
In Journal of Neurorestoratology July 2024
Autor:
Tang, Zhiji, Huang, Weilong, Liu, Lin, Li, Huichen, Meng, Hongliang, Zeng, Tianxiang, Ye, Xinyun, Jiang, Qiuhua, Ye, Y.W., Liu, Yuehua
Publikováno v:
In Journal of Materials Research and Technology January-February 2024 28:3865-3881
Gradient estimation and vector space projection have been studied as two distinct topics. We aim to bridge the gap between the two by investigating how to efficiently estimate gradient based on a projected low-dimensional space. We first provide lowe
Externí odkaz:
http://arxiv.org/abs/2102.13184
Autor:
Tu, James, Li, Huichen, Yan, Xinchen, Ren, Mengye, Chen, Yun, Liang, Ming, Bitar, Eilyan, Yumer, Ersin, Urtasun, Raquel
Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks. Yet, there have been limited
Externí odkaz:
http://arxiv.org/abs/2101.06784
Autor:
Li, Huichen1 (AUTHOR) lllhhhccc2000@163.com, Gao, Jiahao1 (AUTHOR) jhgao2001@163.com, Liu, Yue1 (AUTHOR) ly2742706669@163.com, Ding, Yujia1 (AUTHOR) 18031192772@163.com, Guo, Yusong1 (AUTHOR) ysguo@gdou.edu.cn, Wang, Zhongduo1 (AUTHOR) aduofa@hotmail.com, Dong, Zhongdian1,2 (AUTHOR) zddong@gdou.edu.cn, Zhang, Ning1 (AUTHOR) zddong@gdou.edu.cn
Publikováno v:
Animals (2076-2615). Jan2024, Vol. 14 Issue 2, p222. 13p.
Machine learning (ML), especially deep neural networks (DNNs) have been widely used in various applications, including several safety-critical ones (e.g. autonomous driving). As a result, recent research about adversarial examples has raised great co
Externí odkaz:
http://arxiv.org/abs/2005.14137