Identifying Spammers to Boost Crowdsourced Classification
Identifying Spammers to Boost Crowdsourced Classification
复制标题
识别垃圾邮件发送者以促进众包分类
DOI：
10.1109/icassp39728.2021.9414242
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Giannakis, Georgios B.
中科院分区：
文献类型：
--
作者：
Traganitis, Panagiotis A.;Giannakis, Georgios B.
目前的工作解决了无监督集成或众包分类任务中的对抗性攻击问题。在一定条件下，它示出，无论是分析和通过数值测试，垃圾邮件发送者造成的最大损害分类性能。为了遏制他们的影响，一种新的光谱算法，利用二阶统计的注释者，垃圾邮件检测，合成和真实的数据的初步结果显示这种方法的潜力。
The present work addresses the problem of adversarial attacks in unsupervised ensemble or crowdsourcing classification tasks. Under certain conditions, it is shown, both analytically and through numerical tests, that spammers cause the most damage with respect to classification performance. To curb their effect, a novel spectral algorithm for spammer detection that utilizes second-order statistics of annotators, is developed and preliminary results on synthetic and real data showcase the potential of this approach.