Pub Date : 2019-11-28DOI: 10.1109/TPS-ISA48467.2019.00040
David A. Mohaisen, Songqing Chen
Machine learning techniques are finding many applications in computer systems, including many tasks that require decision making: network optimization, quality of service assurance, and security. We believe machine learning systems are here to stay, and to materialize on their potential we advocate a fresh look at various key issues that need further attention, including security as a requirement and system complexity, and how machine learning systems affect them. We also discuss reproducibility as a key requirement for sustainable machine learning systems, and leads to pursuing it.
{"title":"Computer Systems Have 99 Problems, Let's Not Make Machine Learning Another One","authors":"David A. Mohaisen, Songqing Chen","doi":"10.1109/TPS-ISA48467.2019.00040","DOIUrl":"https://doi.org/10.1109/TPS-ISA48467.2019.00040","url":null,"abstract":"Machine learning techniques are finding many applications in computer systems, including many tasks that require decision making: network optimization, quality of service assurance, and security. We believe machine learning systems are here to stay, and to materialize on their potential we advocate a fresh look at various key issues that need further attention, including security as a requirement and system complexity, and how machine learning systems affect them. We also discuss reproducibility as a key requirement for sustainable machine learning systems, and leads to pursuing it.","PeriodicalId":129820,"journal":{"name":"2019 First IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131900442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-21DOI: 10.1109/TPS-ISA48467.2019.00019
Stacey Truex, Ling Liu, M. E. Gursoy, Wenqi Wei, Lei Yu
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, MPLens, with three unique contributions. First, through MPLens, we demonstrate how membership inference attack methods can be leveraged in adversarial ML. Second, we highlight with MPLens how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data is skewed. We show that risk from membership inference attacks is routinely increased when models use skewed training data. Finally, we investigate the effectiveness of differential privacy as a mitigation technique against membership inference attacks. We discuss the trade-offs of implementing such a mitigation strategy with respect to the model complexity, the learning task complexity, the dataset complexity and the privacy parameter settings.
{"title":"Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability","authors":"Stacey Truex, Ling Liu, M. E. Gursoy, Wenqi Wei, Lei Yu","doi":"10.1109/TPS-ISA48467.2019.00019","DOIUrl":"https://doi.org/10.1109/TPS-ISA48467.2019.00019","url":null,"abstract":"Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, MPLens, with three unique contributions. First, through MPLens, we demonstrate how membership inference attack methods can be leveraged in adversarial ML. Second, we highlight with MPLens how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data is skewed. We show that risk from membership inference attacks is routinely increased when models use skewed training data. Finally, we investigate the effectiveness of differential privacy as a mitigation technique against membership inference attacks. We discuss the trade-offs of implementing such a mitigation strategy with respect to the model complexity, the learning task complexity, the dataset complexity and the privacy parameter settings.","PeriodicalId":129820,"journal":{"name":"2019 First IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133013366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-13DOI: 10.1109/TPS-ISA48467.2019.00039
Benjamin D. Horne, Mauricio G. Gruppi, Sibel Adali
Research in combating misinformation reports many negative results: facts may not change minds, especially if they come from sources that are not trusted. Individuals can disregard and justify lies told by trusted sources. This problem is made even worse by social recommendation algorithms which help amplify conspiracy theories and information confirming one's own biases due to companies' efforts to optimize for clicks and watch time over individuals' own values and public good. As a result, more nuanced voices and facts are drowned out by a continuous erosion of trust in better information sources. Most misinformation mitigation techniques assume that discrediting, filtering, or demoting low veracity information will help news consumers make better information decisions. However, these negative results indicate that some news consumers, particularly extreme or conspiracy news consumers will not be helped. We argue that, given this background, technology solutions to combating misinformation should not simply seek facts or discredit bad news sources, but instead use more subtle nudges towards better information consumption. Repeated exposure to such nudges can help promote trust in better information sources and also improve societal outcomes in the long run. In this article, we will talk about technological solutions that can help us in developing such an approach, and introduce one such model called Trust Nudging.
{"title":"Trustworthy Misinformation Mitigation with Soft Information Nudging","authors":"Benjamin D. Horne, Mauricio G. Gruppi, Sibel Adali","doi":"10.1109/TPS-ISA48467.2019.00039","DOIUrl":"https://doi.org/10.1109/TPS-ISA48467.2019.00039","url":null,"abstract":"Research in combating misinformation reports many negative results: facts may not change minds, especially if they come from sources that are not trusted. Individuals can disregard and justify lies told by trusted sources. This problem is made even worse by social recommendation algorithms which help amplify conspiracy theories and information confirming one's own biases due to companies' efforts to optimize for clicks and watch time over individuals' own values and public good. As a result, more nuanced voices and facts are drowned out by a continuous erosion of trust in better information sources. Most misinformation mitigation techniques assume that discrediting, filtering, or demoting low veracity information will help news consumers make better information decisions. However, these negative results indicate that some news consumers, particularly extreme or conspiracy news consumers will not be helped. We argue that, given this background, technology solutions to combating misinformation should not simply seek facts or discredit bad news sources, but instead use more subtle nudges towards better information consumption. Repeated exposure to such nudges can help promote trust in better information sources and also improve societal outcomes in the long run. In this article, we will talk about technological solutions that can help us in developing such an approach, and introduce one such model called Trust Nudging.","PeriodicalId":129820,"journal":{"name":"2019 First IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)","volume":"248 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134480136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：