Zobrazeno 1 - 10
of 2 309
pro vyhledávání: '"Zhong, Nan"'
Deep models are being applied in numerous fields and have become a new important digital product. Meanwhile, previous studies have shown that deep models are vulnerable to backdoor attacks, in which compromised models return attacker-desired results
Externí odkaz:
http://arxiv.org/abs/2408.00255
Tip leakage flow in turbomachinery inherently generates intense unsteady features, named self-excited unsteadiness, which has not been well understood. A Zonalised LES (ZLES) is employed around a linear cascade, with wall-modelled Large Eddy Simulati
Externí odkaz:
http://arxiv.org/abs/2405.09347
Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack towards image ca
Externí odkaz:
http://arxiv.org/abs/2401.02600
Training a deep neural network (DNN) requires a high computational cost. Buying models from sellers with a large number of computing resources has become prevailing. However, the buyer-seller environment is not always trusted. To protect the neural n
Externí odkaz:
http://arxiv.org/abs/2312.05262
Recent generative models show impressive performance in generating photographic images. Humans can hardly distinguish such incredibly realistic-looking AI-generated images from real ones. AI-generated images may lead to ubiquitous disinformation diss
Externí odkaz:
http://arxiv.org/abs/2311.12397
Backdoor attack aims to compromise a model, which returns an adversary-wanted output when a specific trigger pattern appears yet behaves normally for clean inputs. Current backdoor attacks require changing pixels of clean images, which results in poo
Externí odkaz:
http://arxiv.org/abs/2309.07428
Autor:
Cheng Zhang, Ao-Tong Xiong, Meng-Yi Ren, Yan-Yun Zhao, Min-Jia Huang, Long-Cheng Huang, Zheng Zhang, Yun Wang, Quan-Quan Zheng, Jing Fan, Jing-Jing Guan, Zhong-Nan Yang
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-12 (2024)
Abstract Epigenetic modifications are crucial for plant development. EFD ( E xine F ormation D efect) encodes a SAM-dependent methyltransferase that is essential for the pollen wall pattern formation and male fertility in Arabidopsis. In this study,
Externí odkaz:
https://doaj.org/article/8ce6d8fc9e3f4c6a872ce83768d06b7b
Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manipulating the training dataset or training process. Then, the compromise
Externí odkaz:
http://arxiv.org/abs/2205.03190
Autor:
He, Zhen-feng, Lin, Sheng-zhu, Pan, Cui-xia, Chen, Zhao-ming, Cen, Lai-jian, Zhang, Xiao-xian, Huang, Yan, Chen, Chun-lan, Zha, Shan-shan, Li, Hui-min, Lin, Zhen-hong, Shi, Ming-xin, Zhong, Nan-shan, Guan, Wei-jie
Publikováno v:
In Respiratory Medicine September 2024 231
Publikováno v:
In Food Control August 2024 162