Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Zhu, Shenchen"'
Large Language Models (LLMs) such as ChatGPT and Llama have become prevalent in real-world applications, exhibiting impressive text generation performance. LLMs are fundamentally developed from a scenario where the input data remains static and unstr
Externí odkaz:
http://arxiv.org/abs/2405.20234
Autor:
Lv, Peizhuo, Ma, Hualong, Chen, Kai, Zhou, Jiachen, Zhang, Shengzhi, Liang, Ruigang, Zhu, Shenchen, Li, Pan, Zhang, Yingjun
Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively st
Externí odkaz:
http://arxiv.org/abs/2401.15239
Unlike traditional static deep neural networks (DNNs), dynamic neural networks (NNs) adjust their structures or parameters to different inputs to guarantee accuracy and computational efficiency. Meanwhile, it has been an emerging research area in dee
Externí odkaz:
http://arxiv.org/abs/2210.08956
Autor:
Lv, Peizhuo, Li, Pan, Zhu, Shenchen, Zhang, Shengzhi, Chen, Kai, Liang, Ruigang, Yue, Chang, Xiang, Fan, Cai, Yuling, Ma, Hualong, Zhang, Yingjun, Meng, Guozhu
Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains. However, attackers may stea
Externí odkaz:
http://arxiv.org/abs/2209.03563