如果你能抓住我:欺骗姿态检测和地理标记模型,以保护Twitter上的个人隐私

Dilara Dogan, Bahadir Altun, Muhammed Said Zengin, Mucahid Kutlu, Tamer Elsayed
{"title":"如果你能抓住我:欺骗姿态检测和地理标记模型,以保护Twitter上的个人隐私","authors":"Dilara Dogan, Bahadir Altun, Muhammed Said Zengin, Mucahid Kutlu, Tamer Elsayed","doi":"10.1609/icwsm.v17i1.22136","DOIUrl":null,"url":null,"abstract":"The recent advances in natural language processing have yielded many exciting developments in text analysis and language understanding models; however, these models can also be used to track people, bringing severe privacy concerns. In this work, we investigate what individuals can do to avoid being detected by those models while using social media platforms. We ground our investigation in two exposure-risky tasks, stance detection and geotagging. We explore a variety of simple techniques for modifying text, such as inserting typos in salient words, paraphrasing, and adding dummy social media posts. Our experiments show that the performance of BERT-based models fine-tuned for stance detection decreases significantly due to typos, but it is not affected by paraphrasing. Moreover, we find that typos have minimal impact on state-of-the-art geotagging models due to their increased reliance on social networks; however, we show that users can deceive those models by interacting with different users, reducing their performance by almost 50%.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to Protect Privacy of Individuals on Twitter\",\"authors\":\"Dilara Dogan, Bahadir Altun, Muhammed Said Zengin, Mucahid Kutlu, Tamer Elsayed\",\"doi\":\"10.1609/icwsm.v17i1.22136\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The recent advances in natural language processing have yielded many exciting developments in text analysis and language understanding models; however, these models can also be used to track people, bringing severe privacy concerns. In this work, we investigate what individuals can do to avoid being detected by those models while using social media platforms. We ground our investigation in two exposure-risky tasks, stance detection and geotagging. We explore a variety of simple techniques for modifying text, such as inserting typos in salient words, paraphrasing, and adding dummy social media posts. Our experiments show that the performance of BERT-based models fine-tuned for stance detection decreases significantly due to typos, but it is not affected by paraphrasing. Moreover, we find that typos have minimal impact on state-of-the-art geotagging models due to their increased reliance on social networks; however, we show that users can deceive those models by interacting with different users, reducing their performance by almost 50%.\",\"PeriodicalId\":338112,\"journal\":{\"name\":\"Proceedings of the International AAAI Conference on Web and Social Media\",\"volume\":\"22 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the International AAAI Conference on Web and Social Media\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1609/icwsm.v17i1.22136\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the International AAAI Conference on Web and Social Media","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1609/icwsm.v17i1.22136","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

自然语言处理的最新进展在文本分析和语言理解模型方面取得了许多令人兴奋的进展;然而,这些模型也可以用来跟踪人,带来严重的隐私问题。在这项工作中,我们调查了个人在使用社交媒体平台时可以做些什么来避免被这些模型发现。我们的调查基于两个暴露风险任务,姿态检测和地理标记。我们探索了各种简单的修改文本的技术,例如在突出的单词中插入错别字,释义和添加虚拟的社交媒体帖子。我们的实验表明,基于bert的姿态检测模型的性能由于拼写错误而显著下降,但不受释义的影响。此外,我们发现错别字对最先进的地理标记模型的影响最小,因为它们越来越依赖于社交网络;然而,我们表明,用户可以通过与不同的用户交互来欺骗这些模型,从而使它们的性能降低近50%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to Protect Privacy of Individuals on Twitter
The recent advances in natural language processing have yielded many exciting developments in text analysis and language understanding models; however, these models can also be used to track people, bringing severe privacy concerns. In this work, we investigate what individuals can do to avoid being detected by those models while using social media platforms. We ground our investigation in two exposure-risky tasks, stance detection and geotagging. We explore a variety of simple techniques for modifying text, such as inserting typos in salient words, paraphrasing, and adding dummy social media posts. Our experiments show that the performance of BERT-based models fine-tuned for stance detection decreases significantly due to typos, but it is not affected by paraphrasing. Moreover, we find that typos have minimal impact on state-of-the-art geotagging models due to their increased reliance on social networks; however, we show that users can deceive those models by interacting with different users, reducing their performance by almost 50%.
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
×
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