Zobrazeno 1 - 10
of 1 474
pro vyhledávání: '"Xu, Xiaoyun"'
Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and applicable
Externí odkaz:
http://arxiv.org/abs/2405.19928
Autor:
Zhuang, Zi, Su, Yang, Zhang, Shiyu, Chen, Xuepeng, Yan, Qing-Zeng, Feng, Haoran, Sun, Li, Xu, Xiaoyun, Sun, Yan, Zhou, Xin, Wang, Hongchi, Yang, Ji
We perform a comprehensive CO study toward the Monoceros OB1 (Mon OB1) region based on the MWISP survey at an angular resolution of about $50''$. The high-sensitivity data, together with the high dynamic range, shows that molecular gas in the $\rm 8^
Externí odkaz:
http://arxiv.org/abs/2403.08008
Autor:
Xu, Xiaoyun, Wang, Xiaobing, Muinonen, Karri, Penttil, Antti, Luo, Nanping, Gu, Shenghong, Sun, Leilei, Xu, Fukun, Liu, Yisi, Xiang, Yue, Cao, Dongtao, Wang, Jianhua
The lightcurves of asteroids are essential for determining their physical characteristics, including shape, spin, size, and surface composition. However, most asteroids are missing some of these basic physical parameters due to lack of photometric da
Externí odkaz:
http://arxiv.org/abs/2401.15320
Vision Transformers (ViTs) achieve excellent performance in various tasks, but they are also vulnerable to adversarial attacks. Building robust ViTs is highly dependent on dedicated Adversarial Training (AT) strategies. However, current ViTs' adversa
Externí odkaz:
http://arxiv.org/abs/2312.04960
Publikováno v:
Shipin Kexue, Vol 45, Iss 14, Pp 179-188 (2024)
In order to investigate and evaluate the processibility of broccoli by-products (stems and leaves) and hence to provide a reference for their rational utilization, this study investigated the physicochemical properties and nutritional quality of broc
Externí odkaz:
https://doaj.org/article/7ea9e3af1144424c84543430c41518a0
Publikováno v:
Shipin Kexue, Vol 45, Iss 12, Pp 176-186 (2024)
In this study, headspace solid-phase microextraction-gas chromatography-mass spectrometry (HS-SPME-GC-MS) and liquid chromatography-tandem mass spectrometry (LC-MS/MS) was employed to analyze the composition of volatile organic compounds (VOCs) and l
Externí odkaz:
https://doaj.org/article/088a8e639f164bf9b9e81fa90f950897
In this paper, we propose a novel method, IB-RAR, which uses Information Bottleneck (IB) to strengthen adversarial robustness for both adversarial training and non-adversarial-trained methods. We first use the IB theory to build regularizers as learn
Externí odkaz:
http://arxiv.org/abs/2302.10896
Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (backdoor) attacks. A deep learning model may be poisoned by training with
Externí odkaz:
http://arxiv.org/abs/2302.00747
Autor:
Chen, Xuepeng, Sun, Li, Feng, Jiancheng, Zhang, Shiyu, Guo, Weihua, Xu, Xiaoyun, Su, Yang, Sun, Yan, Zhang, Shaobo, Zhou, Xin, Chen, Zhiwei, Yan, Qing-Zeng, Zhang, Miaomiao, Fang, Min, Yang, Ji
We present wide-field and high-sensitivity CO(1-0) molecular line observations toward the Cassiopeia region, using the 13.7m millimeter telescope of the Purple Mountain Observatory (PMO). The CO observations reveal a large-scale highly filamentary mo
Externí odkaz:
http://arxiv.org/abs/2211.00810
Autor:
Guo, Wenbo, Li, Deping, Zhai, Ying, Xu, Xiaoyun, Qiu, Hao, Miao, Aijun, Cao, Xinde, Zhao, Ling
Publikováno v:
In Environment International November 2024 193