Poster: Backdoor Attacks on Spiking NNs and Neuromorphic Datasets

Gorka Abad, O. Ersoy, S. Picek, Víctor Julio Ramírez-Durán, A. Urbieta
{"title":"Poster: Backdoor Attacks on Spiking NNs and Neuromorphic Datasets","authors":"Gorka Abad, O. Ersoy, S. Picek, Víctor Julio Ramírez-Durán, A. Urbieta","doi":"10.1145/3548606.3563532","DOIUrl":null,"url":null,"abstract":"Neural networks provide state-of-the-art results in many domains. Yet, they often require high energy and time-consuming training processes. Therefore, the research community is exploring alternative, energy-efficient approaches likespiking neural networks (SNNs). SNNs mimic brain neurons by encoding data into sparse spikes, resulting in energy-efficient computing. To exploit the properties of the SNNs, they can be trained with neuromorphic datasets that capture the differences in motion. SNNs, just like any neural network model, can be susceptible to security threats that make the model perform anomalously. One of the most crucial threats is the backdoor attacks that modify the training set to inject a trigger in some samples. After training, the neural network will perform correctly on the main task. However, under the presence of the trigger (backdoor) on an input sample, the attacker can control its behavior. The existing works on backdoor attacks consider standard datasets and not neuromorphic ones. In this paper, to the best of our knowledge, we present the first backdoor attacks on neuromorphic datasets. Due to the structure of neuromorphic datasets, we utilize two different triggers, i.e., static andmoving triggers. We then evaluate the performance of our backdoor using spiking neural networks, achieving top accuracy on both main and backdoor tasks, up to 99%.","PeriodicalId":435197,"journal":{"name":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3548606.3563532","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Neural networks provide state-of-the-art results in many domains. Yet, they often require high energy and time-consuming training processes. Therefore, the research community is exploring alternative, energy-efficient approaches likespiking neural networks (SNNs). SNNs mimic brain neurons by encoding data into sparse spikes, resulting in energy-efficient computing. To exploit the properties of the SNNs, they can be trained with neuromorphic datasets that capture the differences in motion. SNNs, just like any neural network model, can be susceptible to security threats that make the model perform anomalously. One of the most crucial threats is the backdoor attacks that modify the training set to inject a trigger in some samples. After training, the neural network will perform correctly on the main task. However, under the presence of the trigger (backdoor) on an input sample, the attacker can control its behavior. The existing works on backdoor attacks consider standard datasets and not neuromorphic ones. In this paper, to the best of our knowledge, we present the first backdoor attacks on neuromorphic datasets. Due to the structure of neuromorphic datasets, we utilize two different triggers, i.e., static andmoving triggers. We then evaluate the performance of our backdoor using spiking neural networks, achieving top accuracy on both main and backdoor tasks, up to 99%.
海报:对尖峰神经网络和神经形态数据集的后门攻击
神经网络在许多领域提供了最先进的结果。然而,他们往往需要高能量和耗时的培训过程。因此,研究界正在探索替代的节能方法,如峰值神经网络(snn)。snn通过将数据编码成稀疏的尖峰来模拟大脑神经元,从而实现节能计算。为了利用snn的特性,可以用捕捉运动差异的神经形态数据集来训练它们。snn,就像任何神经网络模型一样,可能容易受到安全威胁的影响,从而使模型执行异常。最关键的威胁之一是后门攻击,它修改训练集,在某些样本中注入触发器。经过训练,神经网络将正确执行主要任务。然而,在输入样本上存在触发器(后门)的情况下,攻击者可以控制其行为。现有的后门攻击工作考虑的是标准数据集,而不是神经形态的数据集。在本文中,据我们所知,我们提出了第一个对神经形态数据集的后门攻击。由于神经形态数据集的结构,我们使用两种不同的触发器,即静态和移动触发器。然后,我们使用尖峰神经网络评估我们的后门的性能,在主任务和后门任务上都达到了最高的准确率,高达99%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信