权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Machine Learning and Digital Watermarking in Adversarial Environments

对抗环境中的机器学习和数字水印

基本信息

批准号：
393063728
负责人：
Professor Dr. Konrad Rieck
金额：
--
依托单位：
Fachgebiet Maschinelles Lernen und IT-Sicherheit
依托单位国家：
德国
项目类别：
Research Grants
财政年份：
2017
资助国家：
德国
起止时间：
2016-12-31 至 2021-12-31
项目状态：
已结题

来源：
https://gepris.dfg.de/gepris/projekt/393063728?language=en
关键词：
Machine Learning Digital Watermarking Adversarial

项目摘要

Machine learning algorithms are increasingly used in security-critical applications, such as for detection of malicious software or the control of autonomous vehicles. In these applications, it is crucial that the employed algorithms are not evaded or deceived by an adversary. Unfortunately, most learning algorithms are not robust against attacks and, in the last years, the research field of adversarial machine learning has been established to develop novel attack and defense mechanisms for machine learning.Concurrent to this work, the research area of digital watermarking has tackled similar problems. Digital watermarking aims at marking media, such as images and audio, such that the watermark cannot be removed or extracted by an adversary. Although the research goals of machine learning and watermarking are fundamentally different, there are surprising parallels in the corresponding attack strategies. In both areas, the adversary aims at evading a detection system: (a) in the case of machine learning by deceiving a classification and (b) in the case of digital watermarking by rendering the watermark undetectable.So far, this similarity of both areas have not gained attention in the research communities and it is the goal of this project to systematically study, formalise and join research concepts where possible. Based on a formal framework, attacks as well as defenses from one research area shall be transferred to the other and vice versa. This shall enable the development of novel security mechanisms for both areas and initiate novel directions of joint research.

机器学习算法越来越多地用于安全关键型应用，例如检测恶意软件或控制自动驾驶汽车。在这些应用程序中，至关重要的是，所采用的算法不会被对手逃避或欺骗。不幸的是，大多数学习算法对攻击的鲁棒性不强，在过去的几年里，对抗性机器学习的研究领域已经建立，开发新的攻击和防御机制的机器学习。数字水印旨在标记媒体，例如图像和音频，使得水印不能被对手移除或提取。虽然机器学习和水印的研究目标有着本质的不同，但在相应的攻击策略上却有着惊人的相似之处。在这两个领域中，对手的目的是逃避检测系统：（a）在机器学习的情况下，通过欺骗分类，（B）在数字水印的情况下，通过使水印不可检测。到目前为止，这两个领域的相似性还没有得到研究界的关注，这是本项目的目标，系统地研究，形式化和加入研究概念，在可能的情况下。基于一个正式的框架，攻击以及防御从一个研究领域应转移到另一个，反之亦然。这将有助于为这两个领域制定新的安全机制，并启动新的联合研究方向。