Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Hou, Xiaolu"'
Embedded devices with neural network accelerators offer great versatility for their users, reducing the need to use cloud-based services. At the same time, they introduce new security challenges in the area of hardware attacks, the most prominent bei
Externí odkaz:
http://arxiv.org/abs/2407.16467
Autor:
Chen, Jiawei, Yang, Dingkang, Wu, Tong, Jiang, Yue, Hou, Xiaolu, Li, Mingcheng, Wang, Shunli, Xiao, Dongling, Li, Ke, Zhang, Lihua
Large Vision Language Models (LVLMs) are increasingly integral to healthcare applications, including medical visual question answering and imaging report generation. While these models inherit the robust capabilities of foundational Large Language Mo
Externí odkaz:
http://arxiv.org/abs/2406.10185
Fault injection attacks are a potent threat against embedded implementations of neural network models. Several attack vectors have been proposed, such as misclassification, model extraction, and trojan/backdoor planting. Most of these attacks work by
Externí odkaz:
http://arxiv.org/abs/2405.13891
Autor:
Chen, Jiawei, Yang, Dingkang, Jiang, Yue, Li, Mingcheng, Wei, Jinjie, Hou, Xiaolu, Zhang, Lihua
In the realm of Medical Visual Language Models (Med-VLMs), the quest for universal efficient fine-tuning mechanisms remains paramount, especially given researchers in interdisciplinary fields are often extremely short of training resources, yet large
Externí odkaz:
http://arxiv.org/abs/2404.16385
Model extraction attacks have been widely applied, which can normally be used to recover confidential parameters of neural networks for multiple layers. Recently, side-channel analysis of neural networks allows parameter extraction even for networks
Externí odkaz:
http://arxiv.org/abs/2303.18132
Autor:
Wang, Jianzu, Shi, Xin, Hou, Xiaolu, Chen, Xi, Wang, Qiong, Zhen, Haozhi, Wang, Yuxiao, Li, Xuanjun, Li, Yuan, Shi, Lei
Publikováno v:
In Molecular Catalysis 15 July 2024 564
Neural network implementations are known to be vulnerable to physical attack vectors such as fault injection attacks. As of now, these attacks were only utilized during the inference phase with the intention to cause a misclassification. In this work
Externí odkaz:
http://arxiv.org/abs/2109.11249
Neural networks have been shown to be vulnerable against fault injection attacks. These attacks change the physical behavior of the device during the computation, resulting in a change of value that is currently being computed. They can be realized b
Externí odkaz:
http://arxiv.org/abs/2002.11021
Publikováno v:
In Colloids and Surfaces A: Physicochemical and Engineering Aspects 20 September 2023 673
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.