基于最小不确定性的深度神经网络对手检测

Fatemeh Sheikholeslami, Swayambhoo Jain, G. Giannakis
{"title":"基于最小不确定性的深度神经网络对手检测","authors":"Fatemeh Sheikholeslami, Swayambhoo Jain, G. Giannakis","doi":"10.1109/ITA50056.2020.9244964","DOIUrl":null,"url":null,"abstract":"Despite their unprecedented performance in various domains, utilization of Deep Neural Networks (DNNs) in safety-critical environments is severely limited in the presence of even small adversarial perturbations. The present work develops a randomized approach to detecting such perturbations based on minimum uncertainty metrics that rely on sampling at the hidden layers during the DNN inference stage. Inspired by Bayesian approaches to uncertainty estimation, the sampling probabilities are designed for effective detection of the adversarially corrupted inputs. Being modular, the novel detector of adversaries can be conveniently employed by any pre-trained DNN at no extra training overhead. Selecting which units to sample per hidden layer entails quantifying the amount of DNN output uncertainty, where the overall uncertainty is expressed in terms of its layer-wise components - what also promotes scalability. Sampling probabilities are then sought by minimizing uncertainty measures layer-by-layer, leading to a novel convex optimization problem that admits an exact solver with superlinear convergence rate. By simplifying the objective function, low-complexity approximate solvers are also developed. In addition to valuable insights, these approximations link the novel approach with state-of-the-art randomized adversarial detectors. The effectiveness of the novel detectors in the context of competing alternatives is highlighted through extensive tests for various types of adversarial attacks with variable levels of strength.","PeriodicalId":137257,"journal":{"name":"2020 Information Theory and Applications Workshop (ITA)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"21","resultStr":"{\"title\":\"Minimum Uncertainty Based Detection of Adversaries in Deep Neural Networks\",\"authors\":\"Fatemeh Sheikholeslami, Swayambhoo Jain, G. Giannakis\",\"doi\":\"10.1109/ITA50056.2020.9244964\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Despite their unprecedented performance in various domains, utilization of Deep Neural Networks (DNNs) in safety-critical environments is severely limited in the presence of even small adversarial perturbations. The present work develops a randomized approach to detecting such perturbations based on minimum uncertainty metrics that rely on sampling at the hidden layers during the DNN inference stage. Inspired by Bayesian approaches to uncertainty estimation, the sampling probabilities are designed for effective detection of the adversarially corrupted inputs. Being modular, the novel detector of adversaries can be conveniently employed by any pre-trained DNN at no extra training overhead. Selecting which units to sample per hidden layer entails quantifying the amount of DNN output uncertainty, where the overall uncertainty is expressed in terms of its layer-wise components - what also promotes scalability. Sampling probabilities are then sought by minimizing uncertainty measures layer-by-layer, leading to a novel convex optimization problem that admits an exact solver with superlinear convergence rate. By simplifying the objective function, low-complexity approximate solvers are also developed. In addition to valuable insights, these approximations link the novel approach with state-of-the-art randomized adversarial detectors. The effectiveness of the novel detectors in the context of competing alternatives is highlighted through extensive tests for various types of adversarial attacks with variable levels of strength.\",\"PeriodicalId\":137257,\"journal\":{\"name\":\"2020 Information Theory and Applications Workshop (ITA)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-04-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"21\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Information Theory and Applications Workshop (ITA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITA50056.2020.9244964\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Information Theory and Applications Workshop (ITA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITA50056.2020.9244964","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 21

摘要

尽管深度神经网络(dnn)在各个领域都有前所未有的表现,但在安全关键环境中,即使存在很小的对抗性扰动,深度神经网络(dnn)的应用也受到严重限制。目前的工作开发了一种随机方法来检测这种扰动,该方法基于最小不确定性度量,该度量依赖于DNN推理阶段隐藏层的采样。受贝叶斯方法不确定性估计的启发,采样概率被设计用于有效检测对抗性损坏的输入。由于是模块化的,新的对手检测器可以方便地由任何预训练的DNN使用,而不需要额外的训练开销。选择每个隐藏层采样的单元需要量化DNN输出不确定性的数量,其中整体不确定性以其分层组件表示——这也促进了可扩展性。然后,通过逐层最小化不确定性度量来寻求采样概率,从而导致一种新的凸优化问题,该问题允许具有超线性收敛速率的精确求解器。通过对目标函数的简化,提出了低复杂度的近似解。除了有价值的见解之外,这些近似将新方法与最先进的随机对抗性检测器联系起来。通过对不同强度的各种类型的对抗性攻击进行广泛测试,突出了新型检测器在竞争性替代方案背景下的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Minimum Uncertainty Based Detection of Adversaries in Deep Neural Networks
Despite their unprecedented performance in various domains, utilization of Deep Neural Networks (DNNs) in safety-critical environments is severely limited in the presence of even small adversarial perturbations. The present work develops a randomized approach to detecting such perturbations based on minimum uncertainty metrics that rely on sampling at the hidden layers during the DNN inference stage. Inspired by Bayesian approaches to uncertainty estimation, the sampling probabilities are designed for effective detection of the adversarially corrupted inputs. Being modular, the novel detector of adversaries can be conveniently employed by any pre-trained DNN at no extra training overhead. Selecting which units to sample per hidden layer entails quantifying the amount of DNN output uncertainty, where the overall uncertainty is expressed in terms of its layer-wise components - what also promotes scalability. Sampling probabilities are then sought by minimizing uncertainty measures layer-by-layer, leading to a novel convex optimization problem that admits an exact solver with superlinear convergence rate. By simplifying the objective function, low-complexity approximate solvers are also developed. In addition to valuable insights, these approximations link the novel approach with state-of-the-art randomized adversarial detectors. The effectiveness of the novel detectors in the context of competing alternatives is highlighted through extensive tests for various types of adversarial attacks with variable levels of strength.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Massive MIMO is Very Useful for Pilot-Free Uplink Communications Simplified Ray Tracing for the Millimeter Wave Channel: A Performance Evaluation On Marton's Achievable Region: Local Tensorization for Product Channels with a Binary Component Improve Robustness of Deep Neural Networks by Coding On Nonnegative CP Tensor Decomposition Robustness to Noise
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1