检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Benbouzid, Djalel Plociennik, Christiane Lucaj, Laura Maftei, Mihai Merget, Iris Burchardt, Aljoscha Hauer, Marc P. Naceri, Abdeldjallil van der Smagt, Patrick Machine Learning Research Lab Volkswagen Group Munich Germany Germany Algorithm Accountability Lab TU Kaiserslautern Germany Munich Germany

The growing adoption and deployment of Machine Learning (ML) systems came with its share of ethical incidents and societal concerns. It also unveiled the necessity to properly audit these systems in light of ethical principles. For such a novel type of algorithmic auditing to become standard practice, two main prerequisites need to be available: A lifecycle model that is tailored towards transparency and accountability, and a principled risk assessment procedure that allows the proper scoping of the audit. Aiming to make a pragmatic step towards a wider adoption of ML auditing, we present a respective procedure that extends the AI-HLEG guidelines published by the European Commission. Our audit procedure is based on an ML lifecycle model that explicitly focuses on documentation, accountability, and quality assurance;and serves as a common ground for alignment between the auditors and the audited organisation. We describe two pilots conducted on real-world use cases from two different organisations and discuss the shortcomings of ML algorithmic auditing as well as future directions thereof. © 2024, CC BY-SA.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Crucial Challenges in Large-Scale Black Box Analyses 1

引用

2nd International Workshop on algorithmic Bias in Search and Recommendation, BIAS 2021

作者： Krafft, Tobias D. Reber, Martin Krafft, Roman Coutrier, Anna Zweig, Katharina A. Algorithm Accountability Lab Technische Universität Kaiserslautern Kaiserslautern Germany Science Technology and Innovation Studies University of Edinburgh Edinburgh United Kingdom

ISBN: (数字)9783030788186

ISBN: (纸本)9783030788179

To hold software service and platform providers accountable, it is necessary to create trustworthy, quantified evidence of problematic algorithmic decisions, e.g., by large-scale black box analyses. In this article, we summarize typical and general challenges that arise when such studies are conducted. Those challenges were encountered in multiple black box analyses we conducted, among others in a recent study to quantify, whether Google searches result in search results and ads for unproven stem cell therapies when patients research their disease and possible therapies online. We characterize the challenges by the approach to the black box analysis, and summarize some of the lessons we learned and solutions, that will generalize well to all kinds of large-scale black box analyses. While the studies we base this article on where one-time studies with an explorative character, we conclude the article with some challenges and open questions that need to be solved to hold software service and platform providers accountable with the help of permanent, large-scale black box analyses. © 2021, Springer Nature Switzerland AG.

关键词： Stem cells

来源：评论

学校读者我要写书评

暂无评论

Why do we need to be bots? What prevents society from detecting biases in recommendation systems 1

引用

1st International Workshop on algorithmic Bias in Search and Recommendation, BIAS 2020, held as part of the 42nd European Conference on Information Retrieval, ECIR 2020

作者： Krafft, Tobias D. Hauer, Marc P. Zweig, Katharina A. Algorithm Accountability Lab Technische Universität Kaiserslautern Kaiserslautern Germany

ISBN: (数字)9783030524852

ISBN: (纸本)9783030524845

Concerns about social networks manipulating the (general) public opinion have become a recurring theme in recent years. Whether such an impact actually exists could so far only be tested to a very limited extent. Yet to guarantee the accountability of recommendation and information filtering systems, society needs to be able to determine whether they comply with ethical and legal requirements. This paper focuses on black box analyses as methods that are designed to systematically assess the performance of such systems, but that are, at the same time, not very intrusive. We describe the conditions that must be met to allow black box analyses of recommendation systems based on an application on Facebook’s News Feed. While black box analyses have proven to be useful in the past, several barriers can easily get in the way, such as a limited possibility of automated account control, bot detection and bot inhibition. Drawing on the insights from our case study and the state of the art of research on algorithmic accountability, we formulate several policy demands that need to be met in order to allow monitoring of ADM systems for their compliance with social values. © Springer Nature Switzerland AG 2020.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Using Assurance Cases to assure the fulfillment of non-functional requirements of AI-based systems - Lessons learned

Using Assurance Cases to assure the fulfillment of non-funct...

引用

IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW

作者： Marc P. Hauer Lena Müller-Kress Gertraud Leimüller Katharina Zweig Algorithm Accountability Lab RPTU Kaiserslautern-Landau Germany fAIr by Design Winnovation Consulting Gmbh Austria fAIr by Design Winnovation Consulting Gmbh & Leiwand.ai Gmbh Austria

While AI as a cross-sector technology is applied to more and more use cases and contexts, concerns and questions about the impact of this use on the people involved and society as a whole are increasing. Many companies want to act on these concerns and put a high emphasize on the ethical and fair use of AI in their use cases. But up to date easily applicable methods to translate ethical values, such as fairness, into technical specifications are often missing. One method to do so previously described in literature is the development of an Assurance Case. An Assurance Case presents the argument structure of how a claim ("The system is fair") can be substantiated by evidences like tests. To test the application of the method for fairness requirements in the real world and derive important insights for future use, the method was tested with the real life use case of a software product, which assigns positions in the training of doctors in *** testing the method in a real life setting, it was possible to develop it further and both, increase its usability and facilitate the focus on ethical aspects such as *** questions were: Can the method of Assurance Cases be used to enhance fairness of an AI system? What is the application like in an industry context? How can one improve the method of Assurance Cases to be applicable for the assessment of fairness in AI systems?Together with developers, software and domain experts as well as AI and Open Innovation experts and researchers, the method was applied to the use case of an industry *** insights are that the developed Assurance Case is of great help to the industry partner, especially when thinking about future adaptions, communication and potential regulations or required evidences to support their claim of a fair system. Based on the insights derived from testing the process, the method can be improved, enabling it to be applied more efficiently on future use cases and thus enhancing the

关键词： Industries Training Software testing Ethics Technological innovation Medical services Software

来源：评论

学校读者我要写书评

暂无评论

Assuring Fairness of algorithmic Decision Making

Assuring Fairness of Algorithmic Decision Making

引用

IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW

作者： Marc P. Hauer Rasmus Adler Katharina Zweig Algorithm Accountability Lab TU Kaiserslautern Germany Fraunhofer IESE Kaiserslautern Germany

ISBN: (纸本)9781665444576

Assuring fairness of an algorithmic decision making (ADM) system is a challenging task involving different and possibly conflicting views on fairness as expressed by multiple fairness measures. We argue that a combination of the agile development framework Acceptance Test-Driven Development (ATDD) and the concept of Assurance Cases from safety engineering is a pragmatic way to assure fairness levels that are adequate for a predefined application. The approach supports examinations by regulating bodies or related auditing processes by providing a structured argument explaining the achieved level of fairness and its sufficiency for the application.

关键词： Software testing Conferences Decision making Software algorithms Safety Task analysis Pragmatics

来源：评论

学校读者我要写书评

暂无评论

The Crucial Role of Sensitive Attributes in Fair Classification

The Crucial Role of Sensitive Attributes in Fair Classificat...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Maryam Amir Haeri Katharina Anna Zweig Algorithm Accountability Lab University of Kaiserslautern Kaiserslautern Germany

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

In many countries, it is illegal to make certain decisions based on sensitive attributes such as gender or race. This is because historically, sensitive attributes of individuals were exploited to abuse the rights of individuals, leading to unfair decisions. This view is extended to algorithmic decision-making systems (ADMs) where similar to humans, ADMs should not use sensitive attributes for input. We reject the extension of law from humans to machines, since contrary to humans, algorithms are explicit in their decisions, and the fairness of their decision can be studied independently of their input. The main purpose of this paper is to study and discuss the importance of using sensitive attributes in fair classification systems. Specifically, we suggest two statistical tests on the training dataset, to evaluate whether using sensitive attributes may have an impact on the quality and fairness of prospective classification algorithms. These statistical tests compare the distribution and data complexity of the training dataset between groups identified by the same value for sensitive attributes (e.g., men vs. women). We evaluated our fairness tests on several datasets. It was shown that, the removal of sensitive attributes may result in the decrease of the fairness of ADMs. The results were confirmed by designing and implementing simple classifiers on each dataset (with and without the sensitive attributes). Therefore, the use of sensitive attributes must be evaluated per dataset and algorithm, and ignoring them blindly may result in unfair ADMs.

关键词： Mathematical model Data models Machine learning Linear programming Training data Learning systems Training

来源：评论

学校读者我要写书评

暂无评论

Data Donations for Mapping Risk in Google Search of Health Queries: A case study of unproven stem cell treatments in SEM

Data Donations for Mapping Risk in Google Search of Health Q...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Martin Reber Tobias D. Krafft Roman Krafft Katharina A. Zweig Anna Couturier Algorithm Accountability Technische Universität Kaiserslautern Germany Algorithm Accountability Lab Technische Universität Kaiserslautern Germany Science Technology and Innovation Studies University of Edinburgh Scotland United Kingdom

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

On October 1st, 2019 in response to critique from patient advocates and the medical community, Google explicitly prohibited promotion of unproven stem cell and gene therapy treatments on their platform in order to protect users from rising direct-to-consumer marketing of unproven medical interventions. This project aims to record the efficacy of that prohibition as it was enforced and track the impact of Google's AI-based advertising modalities on end-user results. In particular, this study gives special consideration to the risk potential for vulnerable patient communities navigating health information through Google search. Utilising a crowd-sourced `Black Box' audit with a browser plugin, we captured the continued presence of prohibited and problematic advertisements returned by stem cell-related queries in the months following Google's ban. In the domain of Search Engine Marketing (SEM), emerging stem cell treatments are situated in a critical juncture between advertisers and potentially vulnerable users with Google Search as an unobserved mediator. Addressing the issues raised by this data collection is of utmost importance in the protection of patient populations online. This project aims to draw attention to the need for transparency and accountability of advertising intermediaries engaged in the targeted promotion of potentially problematic treatments to vulnerable audiences.

关键词： Internet Stem cells Browsers Advertising Search engines Industries Multiple sclerosis

来源：评论

学校读者我要写书评

暂无评论

Towards a common testing terminology for Software Engineering and data science experts

arXiv

引用

arXiv 2021年

作者： Jöckel, Lisa Bauer, Thomas M., Kläs M.P., Hauer J., Groß Fraunhofer Institute for Experimental Software Engineering IESE Fraunhofer-Platz 1 Kaiserslautern67663 Germany Algorithm Accountability Lab TU Kaiserslautern Gottlieb-Daimler-Strasse 48 Kaiserslautern67663 Germany

Analytical quality assurance, especially testing, is an integral part of software-intensive system development. With the increased usage of Artificial Intelligence (AI) and Machine Learning (ML) as part of such systems, this becomes more difficult as well-understood software testing approaches cannot be applied directly to the AI-enabled parts of the system. The required adaptation of classical testing approaches and the development of new concepts for AI would benefit from a deeper understanding and exchange between AI and software engineering experts. We see the different terminologies used in the two communities as a major obstacle on this way. As we consider a mutual understanding of the testing terminology a key, this paper contributes a mapping between the most important concepts from classical software testing and AI testing. In the mapping, we highlight differences in the relevance and naming of the mapped concepts. Copyright © 2021, The Authors. All rights reserved.

关键词： Quality assurance

来源：评论

学校读者我要写书评

暂无评论

Masterarbeit

arXiv

引用

arXiv 2018年

作者： Krafft, Tobias D. Algorithm Accountability Lab Fachbereich Informatik TECHNISCHE UNIVERSITÄT KAISERSLAUTERN

In this methodology, such an evaluation is conducted by implementing a common machine learning approach called binary classifier, as it determines the binary outcome of the underlying juristic question. This thesis showed that the PPVk (positive predictive value) technique models the decision of judges much better than the AUC. Therefore, this research has investigated whether there exists a classifier for which the PPVk deviates from AUC by a large proportion. It could be shown that the deviation can rise up to 0.75. In order to test this deviation on an already in used Classifier, data from the fourth generation risk assement tool COMPAS was used. The result were were quite alarming as the two measures derivate from each other by *** this study, the risk assessment evaluation of the forecasting tools was successfully conducted, carefully reviewed and examined. Additionally, it is also discussed whether such systems used for the purpose of making decisions should be socially accepted or *** master’s thesis discusses an important issue regarding how algorithmic decision making (ADM) is used in crime forecasting. In America forecasting tools are widely used by judiciary systems for making decisions about risk offenders based on criminal justice for risk offenders. By making use of such tools, the judiciary relies on ADM in order to make error free judgement on offenders. For this purpose, one of the quality measures for machine learning techniques which is widly used, the AUC (area under curve), is compared to and contrasted for results with the PPVk (positive predictive value). Keeping in view the criticality of judgement along with a high dependency on tools offering ADM, it is necessary to evaluate risk tools that aid in decision making based on algorithms. Copyright © 2018, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Postmortem Analysis of Decayed Online Social Communities: Cascade Pattern Analysis and Prediction

arXiv

引用

arXiv 2018年

作者： Abufouda, Mohammed Algorithm Accountability Lab Computer Science Department University of Kaiserslautern Germany

Recently, many online social networks, such as MySpace, Orkut, and Friendster, have faced inactivity decay of their members, which contributed to the collapse of these networks. The reasons, mechanics, and prevention mechanisms of such inactivity decay are not fully understood. In this work, we analyze decayed and alive subwebsites from the Stack Exchange platform. The analysis mainly focuses on the inactivity cascades that occur among the members of these communities. We provide measures to understand the decay process and statistical analysis to extract the patterns that accompany the inactivity decay. Additionally, we predict cascade size and cascade virality using machine learning. The results of this work include a statistically significant difference of the decay patterns between the decayed and the alive subwebsites. These patterns are mainly cascade size, cascade virality, cascade duration, and cascade similarity. Additionally, the contributed prediction framework showed satisfactorily prediction results compared to a baseline predictor. Supported by empirical evidence, the main findings of this work are (1) there are significantly different decay patterns in the alive and the decayed subwebsites of the Stack Exchange;(2) the cascade’s node degrees contribute more to the decay process than the cascade’s virality, which indicates that the expert members of the Stack Exchange subwebsites were mainly responsible for the activity or inactivity of the Stack Exchange subwebsites;(3) the Statistics subwebsite is going through decay dynamics that may lead to it becoming fully-decayed;(4) the decay process is not governed by only one network measure, it is better described using multiple measures;(5) decayed subwebsites were originally less resilient to inactivity decay, unlike the alive subwebsites;and (6) network’s structure in the early stages of its evolution dictates the activity/inactivity characteristics of the network. Copyright © 2018, The Authors. All right

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：