Elizabeth Bondi-Kelly, Lily Xu, Diana Acosta-Navas, J. Killian
Research in artificial intelligence (AI) for social good presupposes some definition of social good, but potential definitions have been seldom suggested and never agreed upon. The normative question of what AI for social good research should be "for" is not thoughtfully elaborated, or is frequently addressed with a utilitarian outlook that prioritizes the needs of the majority over those who have been historically marginalized, brushing aside realities of injustice and inequity. We argue that AI for social good ought to be assessed by the communities that the AI system will impact, using as a guide the capabilities approach, a framework to measure the ability of different policies to improve human welfare equity. Furthermore, we lay out how AI research has the potential to catalyze social progress by expanding and equalizing capabilities. We show how the capabilities approach aligns with a participatory approach for the design and implementation of AI for social good research in a framework we introduce called PACT, in which community members affected should be brought in as partners and their input prioritized throughout the project. We conclude by providing an incomplete set of guiding questions for carrying out such participatory AI research in a way that elicits and respects a community's own definition of social good.
{"title":"Envisioning Communities: A Participatory Approach Towards AI for Social Good","authors":"Elizabeth Bondi-Kelly, Lily Xu, Diana Acosta-Navas, J. Killian","doi":"10.1145/3461702.3462612","DOIUrl":"https://doi.org/10.1145/3461702.3462612","url":null,"abstract":"Research in artificial intelligence (AI) for social good presupposes some definition of social good, but potential definitions have been seldom suggested and never agreed upon. The normative question of what AI for social good research should be \"for\" is not thoughtfully elaborated, or is frequently addressed with a utilitarian outlook that prioritizes the needs of the majority over those who have been historically marginalized, brushing aside realities of injustice and inequity. We argue that AI for social good ought to be assessed by the communities that the AI system will impact, using as a guide the capabilities approach, a framework to measure the ability of different policies to improve human welfare equity. Furthermore, we lay out how AI research has the potential to catalyze social progress by expanding and equalizing capabilities. We show how the capabilities approach aligns with a participatory approach for the design and implementation of AI for social good research in a framework we introduce called PACT, in which community members affected should be brought in as partners and their input prioritized throughout the project. We conclude by providing an incomplete set of guiding questions for carrying out such participatory AI research in a way that elicits and respects a community's own definition of social good.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133782471","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}
The use of video surveillance in public spaces--both by government agencies and by private citizens--has attracted considerable attention in recent years, particularly in light of rapid advances in face-recognition technology. But it has been difficult to systematically measure the prevalence and placement of cameras, hampering efforts to assess the implications of surveillance on privacy and public safety. Here we present a novel approach for estimating the spatial distribution of surveillance cameras: applying computer vision algorithms to large-scale street view image data. Specifically, we build a camera detection model and apply it to 1.6 million street view images sampled from 10 large U.S. cities and 6 other major cities around the world, with positive model detections verified by human experts. After adjusting for the estimated recall of our model, and accounting for the spatial coverage of our sampled images, we are able to estimate the density of surveillance cameras visible from the road. Across the 16 cities we consider, the estimated number of surveillance cameras per linear kilometer ranges from 0.1 (in Seattle) to 0.9 (in Seoul). In a detailed analysis of the 10 U.S. cities, we find that cameras are concentrated in commercial, industrial, and mixed zones, and in neighborhoods with higher shares of non-white residents---a pattern that persists even after adjusting for land use. These results help inform ongoing discussions on the use of surveillance technology, including its potential disparate impacts on communities of color.
{"title":"Surveilling Surveillance: Estimating the Prevalence of Surveillance Cameras with Street View Data","authors":"Hao Sheng, Keniel Yao, Sharad Goel","doi":"10.1145/3461702.3462525","DOIUrl":"https://doi.org/10.1145/3461702.3462525","url":null,"abstract":"The use of video surveillance in public spaces--both by government agencies and by private citizens--has attracted considerable attention in recent years, particularly in light of rapid advances in face-recognition technology. But it has been difficult to systematically measure the prevalence and placement of cameras, hampering efforts to assess the implications of surveillance on privacy and public safety. Here we present a novel approach for estimating the spatial distribution of surveillance cameras: applying computer vision algorithms to large-scale street view image data. Specifically, we build a camera detection model and apply it to 1.6 million street view images sampled from 10 large U.S. cities and 6 other major cities around the world, with positive model detections verified by human experts. After adjusting for the estimated recall of our model, and accounting for the spatial coverage of our sampled images, we are able to estimate the density of surveillance cameras visible from the road. Across the 16 cities we consider, the estimated number of surveillance cameras per linear kilometer ranges from 0.1 (in Seattle) to 0.9 (in Seoul). In a detailed analysis of the 10 U.S. cities, we find that cameras are concentrated in commercial, industrial, and mixed zones, and in neighborhoods with higher shares of non-white residents---a pattern that persists even after adjusting for land use. These results help inform ongoing discussions on the use of surveillance technology, including its potential disparate impacts on communities of color.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133084079","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}
Artificial intelligence (AI) is supposed to help us make better choices. Some of these choices are small, like what route to take to work, or what music to listen to. Others are big, like what treatment to administer for a disease or how long to sentence someone for a crime. If AI can assist with these big decisions, we might think it can also help with hard choices, cases where alternatives are neither better, worse nor equal but on a par. The aim of this paper, however, is to show that this view is mistaken: the fact of parity shows that there are hard limits on AI in decision making and choices that AI cannot, and should not, resolve.
{"title":"Hard Choices and Hard Limits in Artificial Intelligence","authors":"B. Goodman","doi":"10.1145/3461702.3462539","DOIUrl":"https://doi.org/10.1145/3461702.3462539","url":null,"abstract":"Artificial intelligence (AI) is supposed to help us make better choices. Some of these choices are small, like what route to take to work, or what music to listen to. Others are big, like what treatment to administer for a disease or how long to sentence someone for a crime. If AI can assist with these big decisions, we might think it can also help with hard choices, cases where alternatives are neither better, worse nor equal but on a par. The aim of this paper, however, is to show that this view is mistaken: the fact of parity shows that there are hard limits on AI in decision making and choices that AI cannot, and should not, resolve.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122706879","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}
M. Afnan, C. Rudin, Vincent Conitzer, J. Savulescu, Abhishek Mishra, Yanhe Liu, M. Afnan
AI has the potential to revolutionize many areas of healthcare. Radiology, dermatology, and ophthalmology are some of the areas most likely to be impacted in the near future, and they have received significant attention from the broader research community. But AI techniques are now also starting to be used in in vitro fertilization (IVF), in particular for selecting which embryos to transfer to the woman. The contribution of AI to IVF is potentially significant, but must be done carefully and transparently, as the ethical issues are significant, in part because this field involves creating new people. We first give a brief introduction to IVF and review the use of AI for embryo selection. We discuss concerns with the interpretation of the reported results from scientific and practical perspectives. We then consider the broader ethical issues involved. We discuss in detail the problems that result from the use of black-box methods in this context and advocate strongly for the use of interpretable models. Importantly, there have been no published trials of clinical effectiveness, a problem in both the AI and IVF communities, and we therefore argue that clinical implementation at this point would be premature. Finally, we discuss ways for the broader AI community to become involved to ensure scientifically sound and ethically responsible development of AI in IVF.
{"title":"Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilization","authors":"M. Afnan, C. Rudin, Vincent Conitzer, J. Savulescu, Abhishek Mishra, Yanhe Liu, M. Afnan","doi":"10.1145/3461702.3462589","DOIUrl":"https://doi.org/10.1145/3461702.3462589","url":null,"abstract":"AI has the potential to revolutionize many areas of healthcare. Radiology, dermatology, and ophthalmology are some of the areas most likely to be impacted in the near future, and they have received significant attention from the broader research community. But AI techniques are now also starting to be used in in vitro fertilization (IVF), in particular for selecting which embryos to transfer to the woman. The contribution of AI to IVF is potentially significant, but must be done carefully and transparently, as the ethical issues are significant, in part because this field involves creating new people. We first give a brief introduction to IVF and review the use of AI for embryo selection. We discuss concerns with the interpretation of the reported results from scientific and practical perspectives. We then consider the broader ethical issues involved. We discuss in detail the problems that result from the use of black-box methods in this context and advocate strongly for the use of interpretable models. Importantly, there have been no published trials of clinical effectiveness, a problem in both the AI and IVF communities, and we therefore argue that clinical implementation at this point would be premature. Finally, we discuss ways for the broader AI community to become involved to ensure scientifically sound and ethically responsible development of AI in IVF.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115683908","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}
This presentation for the AIES '21 doctoral consortium examines the Latin American crowdsourcing market through a decolonial lens. This research is based on the analysis of the web traffic of ninety-three platforms, interviews with Venezuelan data workers of four platforms, and analysis of the documentation issued by these organizations. The findings show that (1) centuries-old global divisions of labor persist, in this case, with requesters located in advanced economies and workers in the Global South. (2) That the platforms' configuration of the labor process constrains the agency of these workers when producing annotations. And, (3) that ideologies originating from the Global North serve to legitimize and reinforce this global labor market configuration.
{"title":"The Coloniality of Data Work in Latin America","authors":"Julian Posada","doi":"10.1145/3461702.3462471","DOIUrl":"https://doi.org/10.1145/3461702.3462471","url":null,"abstract":"This presentation for the AIES '21 doctoral consortium examines the Latin American crowdsourcing market through a decolonial lens. This research is based on the analysis of the web traffic of ninety-three platforms, interviews with Venezuelan data workers of four platforms, and analysis of the documentation issued by these organizations. The findings show that (1) centuries-old global divisions of labor persist, in this case, with requesters located in advanced economies and workers in the Global South. (2) That the platforms' configuration of the labor process constrains the agency of these workers when producing annotations. And, (3) that ideologies originating from the Global North serve to legitimize and reinforce this global labor market configuration.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116455021","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}
How should we understand the social and political effects of the datafication of human life? This paper argues that the effects of data should be understood as a constitutive shift in social and political relations. We explore how datafication, or quantification of human and non-human factors into binary code, affects the identity of individuals and groups. This fundamental shift goes beyond economic and ethical concerns, which has been the focus of other efforts to explore the effects of datafication and AI. We highlight that technologies such as datafication and AI (and previously, the printing press) both disrupted extant power arrangements, leading to decentralization, and triggered a recentralization of power by new actors better adapted to leveraging the new technology. We use the analogy of the printing press to provide a framework for understanding constitutive change. The printing press example gives us more clarity on 1) what can happen when the medium of communication drastically alters how information is communicated and stored; 2) the shift in power from state to private actors; and 3) the tension of simultaneously connecting individuals while driving them towards narrower communities through algorithmic analyses of data.
{"title":"We Haven't Gone Paperless Yet: Why the Printing Press Can Help Us Understand Data and AI","authors":"Julian Posada, N. Weller, W. Wong","doi":"10.1145/3461702.3462604","DOIUrl":"https://doi.org/10.1145/3461702.3462604","url":null,"abstract":"How should we understand the social and political effects of the datafication of human life? This paper argues that the effects of data should be understood as a constitutive shift in social and political relations. We explore how datafication, or quantification of human and non-human factors into binary code, affects the identity of individuals and groups. This fundamental shift goes beyond economic and ethical concerns, which has been the focus of other efforts to explore the effects of datafication and AI. We highlight that technologies such as datafication and AI (and previously, the printing press) both disrupted extant power arrangements, leading to decentralization, and triggered a recentralization of power by new actors better adapted to leveraging the new technology. We use the analogy of the printing press to provide a framework for understanding constitutive change. The printing press example gives us more clarity on 1) what can happen when the medium of communication drastically alters how information is communicated and stored; 2) the shift in power from state to private actors; and 3) the tension of simultaneously connecting individuals while driving them towards narrower communities through algorithmic analyses of data.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117331186","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}
Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Neal Patwari, S. Venkatasubramanian
When it comes to studying the impacts of decision making, the research has been largely focused on examining the fairness of the decisions, the long-term effects of the decision pipelines, and utility-based perspectives considering both the decision-maker and the individuals. However, there has hardly been any focus on precarity which is the term that encapsulates the instability in people's lives. That is, a negative outcome can overspread to other decisions and measures of well-being. Studying precarity necessitates a shift in focus -- from the point of view of the decision-maker to the perspective of the decision subject. This centering of the subject is an important direction that unlocks the importance of parting with aggregate measures to examine the long-term effects of decision making. To address this issue, in this paper, we propose a modeling framework that simulates the effects of compounded decision-making on precarity over time. Through our simulations, we are able to show the heterogeneity of precarity by the non-uniform ruinous aftereffects of negative decisions on different income classes of the underlying population and how policy interventions can help mitigate such effects.
{"title":"Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instability","authors":"Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Neal Patwari, S. Venkatasubramanian","doi":"10.1145/3461702.3462529","DOIUrl":"https://doi.org/10.1145/3461702.3462529","url":null,"abstract":"When it comes to studying the impacts of decision making, the research has been largely focused on examining the fairness of the decisions, the long-term effects of the decision pipelines, and utility-based perspectives considering both the decision-maker and the individuals. However, there has hardly been any focus on precarity which is the term that encapsulates the instability in people's lives. That is, a negative outcome can overspread to other decisions and measures of well-being. Studying precarity necessitates a shift in focus -- from the point of view of the decision-maker to the perspective of the decision subject. This centering of the subject is an important direction that unlocks the importance of parting with aggregate measures to examine the long-term effects of decision making. To address this issue, in this paper, we propose a modeling framework that simulates the effects of compounded decision-making on precarity over time. Through our simulations, we are able to show the heterogeneity of precarity by the non-uniform ruinous aftereffects of negative decisions on different income classes of the underlying population and how policy interventions can help mitigate such effects.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131800231","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}
Meghana Kshirsagar, Caleb Robinson, Siyu Yang, Shahrzad Gholami, I. Klyuzhin, S. Mukherjee, Md Nasir, Anthony Ortiz, Felipe Oviedo, Darren Tanner, Anusua Trivedi, Yixi Xu, Ming Zhong, B. Dilkina, R. Dodhia, J. Ferres
AI for good (AI4G) projects involve developing and applying artificial intelligence (AI) based solutions to further goals in areas such as sustainability, health, humanitarian aid, and social justice. Developing and deploying such solutions must be done in collaboration with partners who are experts in the domain in question and who already have experience in making progress towards such goals. Based on our experiences, we detail the different aspects of this type of collaboration broken down into four high-level categories: communication, data, modeling, and impact, and distill eleven takeaways to guide such projects in the future. We briefly describe two case studies to illustrate how some of these takeaways were applied in practice during our past collaborations.
AI for good (AI4G)项目涉及开发和应用基于人工智能(AI)的解决方案，以实现可持续性、健康、人道主义援助和社会正义等领域的进一步目标。开发和部署此类解决方案必须与相关领域的专家以及已经在实现这些目标方面取得进展的经验的伙伴合作完成。根据我们的经验，我们详细地将这种类型的协作的不同方面分为四个高级类别:通信、数据、建模和影响，并提炼出11个要点来指导未来的此类项目。我们简要地描述了两个案例研究，以说明在我们过去的合作中如何将这些要点应用于实践。
{"title":"Becoming Good at AI for Good","authors":"Meghana Kshirsagar, Caleb Robinson, Siyu Yang, Shahrzad Gholami, I. Klyuzhin, S. Mukherjee, Md Nasir, Anthony Ortiz, Felipe Oviedo, Darren Tanner, Anusua Trivedi, Yixi Xu, Ming Zhong, B. Dilkina, R. Dodhia, J. Ferres","doi":"10.1145/3461702.3462599","DOIUrl":"https://doi.org/10.1145/3461702.3462599","url":null,"abstract":"AI for good (AI4G) projects involve developing and applying artificial intelligence (AI) based solutions to further goals in areas such as sustainability, health, humanitarian aid, and social justice. Developing and deploying such solutions must be done in collaboration with partners who are experts in the domain in question and who already have experience in making progress towards such goals. Based on our experiences, we detail the different aspects of this type of collaboration broken down into four high-level categories: communication, data, modeling, and impact, and distill eleven takeaways to guide such projects in the future. We briefly describe two case studies to illustrate how some of these takeaways were applied in practice during our past collaborations.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126938371","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}
R. Zwetsloot, Baobao Zhang, Noemi Dreksler, L. Kahn, Markus Anderljung, A. Dafoe, Michael C. Horowitz
Countries, companies, and universities are increasingly competing over top-tier artificial intelligence (AI) researchers. Where are these researchers likely to immigrate and what affects their immigration decisions? We conducted a survey (n = 524) of the immigration preferences and motivations of researchers that had papers accepted at one of two prestigious AI conferences: the Conference on Neural Information Processing Systems (NeurIPS) and the International Conference on Machine Learning (ICML). We find that the U.S. is the most popular destination for AI researchers, followed by the U.K., Canada, Switzerland, and France. A country's professional opportunities stood out as the most common factor that influences immigration decisions of AI researchers, followed by lifestyle and culture, the political climate, and personal relations. The destination country's immigration policies were important to just under half of the researchers surveyed, while around a quarter noted current immigration difficulties to be a deciding factor. Visa and immigration difficulties were perceived to be a particular impediment to conducting AI research in the U.S., the U.K., and Canada. Implications of the findings for the future of AI talent policies and governance are discussed.
{"title":"Skilled and Mobile: Survey Evidence of AI Researchers' Immigration Preferences","authors":"R. Zwetsloot, Baobao Zhang, Noemi Dreksler, L. Kahn, Markus Anderljung, A. Dafoe, Michael C. Horowitz","doi":"10.1145/3461702.3462617","DOIUrl":"https://doi.org/10.1145/3461702.3462617","url":null,"abstract":"Countries, companies, and universities are increasingly competing over top-tier artificial intelligence (AI) researchers. Where are these researchers likely to immigrate and what affects their immigration decisions? We conducted a survey (n = 524) of the immigration preferences and motivations of researchers that had papers accepted at one of two prestigious AI conferences: the Conference on Neural Information Processing Systems (NeurIPS) and the International Conference on Machine Learning (ICML). We find that the U.S. is the most popular destination for AI researchers, followed by the U.K., Canada, Switzerland, and France. A country's professional opportunities stood out as the most common factor that influences immigration decisions of AI researchers, followed by lifestyle and culture, the political climate, and personal relations. The destination country's immigration policies were important to just under half of the researchers surveyed, while around a quarter noted current immigration difficulties to be a deciding factor. Visa and immigration difficulties were perceived to be a particular impediment to conducting AI research in the U.S., the U.K., and Canada. Implications of the findings for the future of AI talent policies and governance are discussed.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125839301","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}
Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are directly associated with the training data, releasing such a model raises privacy concerns. In this work, we propose the use of normalizing flow models that provide explicit differential privacy guarantees as a novel approach to the problem of privacy-preserving density estimation. We evaluate the efficacy of our approach empirically using benchmark datasets, and we demonstrate that our method substantially outperforms previous state-of-the-art approaches. We additionally show how our algorithm can be applied to the task of differentially private anomaly detection.
{"title":"Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation","authors":"Chris Waites, Rachel Cummings","doi":"10.1145/3461702.3462625","DOIUrl":"https://doi.org/10.1145/3461702.3462625","url":null,"abstract":"Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are directly associated with the training data, releasing such a model raises privacy concerns. In this work, we propose the use of normalizing flow models that provide explicit differential privacy guarantees as a novel approach to the problem of privacy-preserving density estimation. We evaluate the efficacy of our approach empirically using benchmark datasets, and we demonstrate that our method substantially outperforms previous state-of-the-art approaches. We additionally show how our algorithm can be applied to the task of differentially private anomaly detection.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"33 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126946785","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：