Protecting Visual Secrets Using Adversarial Nets

机译：使用对抗网保护视觉秘密

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Protecting visual secrets is an important problem due to the prevalence of cameras that continuously monitor our surroundings. Any viable solution to this problem should also minimize the impact on the utility of applications that use images. In this work, we build on the existing work of adversarial learning to design a perturbation mechanism that jointly optimizes privacy and utility objectives. We provide a feasibility study of the proposed mechanism and present ideas on developing a privacy framework based on the adversarial perturbation mechanism.

机译：保护视觉秘密是由于摄像机的普遍存在的普遍存在，这是一个不断监测我们周围环境的重要问题。对此问题的任何可行解决方案还应最大限度地减少对使用图像的应用程序的影响。在这项工作中，我们建立了对普遍学习的现有工作来设计一个共同优化隐私和实用目标的扰动机制。我们提供了基于对抗扰动机制的提出机制和现代思路的可行性研究。

著录项

来源
《IEEE Conference on Computer Vision and Pattern Recognition Workshops》|2017年|1 v.|共4页
会议地点
作者
Nisarg Raval; Ashwin Machanavajjhala; Landon P. Cox;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 TP391.41;
关键词
Privacy; Training; Visualization; Cameras; Machine learning; Loss measurement; Feeds;

机译：隐私;培训;可视化;相机;机器学习;损失测量;饲料;

相似文献

外文文献
中文文献
专利

1. Protecting children on the internet using deep generative adversarial networks [J] . Rasim M. Alguliyev, Fargana J. Abdullayeva, Sabira S. Ojagverdiyeva International journal of computational systems engineering . 2020,第2期

机译：使用深生成的对抗网络保护互联网上的儿童
2. Detecting audio adversarial examples for protecting speech-to-text transcription neural networks [J] . Keiichi Tamura, Akitada Omagari, Hajime Ito, International journal of computational intelligence studies . 2021,第2a3期

机译：检测保护语音到文本转录神经网络的音频逆势示例
3. Algorithm Protects Networks by Detecting Adversarial Actions [J] . NASA Tech Briefs . 2020,第10期

机译：算法通过检测对抗动作来保护网络
4. Protecting Visual Secrets Using Adversarial Nets [C] . Nisarg Raval, Ashwin Machanavajjhala, Landon P. Cox IEEE Conference on Computer Vision and Pattern Recognition Workshops . 2017

机译：使用对抗网保护视觉秘密
5. Enhancing Visual Perception in Noisy Environments Using Generative Adversarial Networks [D] . Fabbri, Cameron. 2018

机译：使用生成的对抗网络增强嘈杂环境中的视觉感知
6. DReLAB - Deep REinforcement Learning Adversarial Botnet: A benchmark dataset for adversarial attacks against botnet Intrusion Detection Systems [O] . Andrea Venturi, Giovanni Apruzzese, Mauro Andreolini, 2021

机译：DRELAB - 深度加强学习对抗僵尸网络：用于对僵尸网络入侵检测系统进行对抗性攻击的基准数据集
7. Defense-PointNet: Protecting PointNet Against Adversarial Attacks [O] . Yu Zhang, Gongbo Liang, Tawfiq Salem, 2019

机译：防御报告：保护注意力引起对抗对抗攻击
8. Genetic secrets: Protecting privacy and confidentiality in the genetic era [R] . Rothstein, M. A. 1998

机译：遗传秘密：保护遗传时代的隐私和机密

Protecting Visual Secrets Using Adversarial Nets

摘要

著录项

相似文献

相关主题

期刊订阅