Practical Attacks Against Authorship Recognition Techniques对作者识别技术的实际攻击.pptVIP

下载本文档

2
0
约1.83万字
约 41页
2017-03-08 发布于上海
举报
版权申诉

Practical Attacks Against Authorship Recognition Techniques对作者识别技术的实际攻击.ppt

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Practical Attacks Against Authorship Recognition Techniques对作者识别技术的实际攻击

09/20/09 * Expanding upon imitation attack * 09/20/09 * 09/20/09 * VALIDATION EXPERIMENT ATTACK EXPERIMENT EXPERIMENTAL CONDITIONS * 09/20/09 * -”why is it worth attacking”? -read this quote * 09/20/09 * 09/20/09 * Cite up top * 09/20/09 * * 09/20/09 * (Cite method paper up top) * 09/20/09 * **13-15 MINUTES IN HERE IS FINE** HIGHLIGHT THAT THIS REAFFIRMS FINDINGS OF ORIGINAL STUDIES BUT WITH MORE AUTHORS * 09/20/09 * HIGHLIGHT ORIGINAL GOAL – SECURITY POTENTIAL – THIS GRAPH SUGGESTS THAT WOULD BE PROBLEMATIC * 09/20/09 * * 09/20/09 * 09/20/09 * * 09/20/09 * * 09/20/09 * Obfuscation Attack Detection Obfuscation attacks brought the accuracy of each system to that of random chance or worse. Imitation Attack Detection Imitation attacks all but completely circumvented all three authorship recognition methods. Imitation Attack Success The imitation attacks were very successful in targeting the intended victim of the attack. Questioning the Results Why are some authors more susceptible to attack? Why did certain methods perform better than others? Would these results hold up in a stricter domain? What if the participants were skilled in linguistics or stylometry? What features and methods could offer some resistance to these attacks? Translation Attacks Common suggestion: run some text through a translator and back! Limited testing show this to be ineffective. Translation Test Setup: Five Subjects, (88-98% base accuracy) Single passage translated to/from German and Japanese. Tested on Neural Network Synonym Methods 100% effectiveness in identifying true author. Using Attacks to Improve Privacy * What you can do: Important: These these methods failed, others might not. Best: Try to imitate someone else. Write less. What is needed A tool that will assist in anonymizing writing styles. Building a Tool What a style-modifying tool needs: A variety of methods features. A large corpus of existing authors. AI-Assisted (Human oversight to preserve content) Open Source Non-