Designing Accountable Systems

Kacianka, Severin; Pretschner, Alexander

doi:10.1145/3442188.3445905

Cited by 24 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We focus on creating verifiable claims to support arguments that aim at trustworthy AI [25], by explaining the design and operation of a system, which allows for transparency, causality and ultimately control (e.g. blaming a responsible actor for their actions and introducing countermeasures) [11]. An accountability argument should explain checks and tests performed as well as outcomes to ensure particular system properties.…”

Section: Objectives Of the Afˆ2 Frameworkmentioning

confidence: 99%

“…evidence provided to support the claims could be conflicting and conflicts should be resolvable by the third party. Consequently, the dimensions of accountable FL systems include [11,[28][29][30]:…”

Section: Objectives Of the Afˆ2 Frameworkmentioning

confidence: 99%

“…In this paper, we design FL as an accountable system [11], drawing on some accountability requirements specified for traditional ML: prove adherence to governance, risk and compliance obligations and allow for monitoring and auditing the fulfilment of the latter among multiple parties. In traditional ML, FactSheets [12] have been proposed as a way to enable such accountability by recording "facts" related to the overall ML pipeline, in terms of performance and robustness guarantees, safety and security as well as a lineage of data and model versions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach

Baracaldo¹,

Ali²,

Purcell³

et al. 2022

Preprint

View full text Add to dashboard Cite

Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL is promising regarding privacy, but needs to excel vis-à-vis transparency and trustworthiness. In particular, FL has to address the accountability of the parties involved and their adherence to rules, law and principles. We introduce AFˆ2 Framework , where we instrument FL with accountability by fusing verifiable claims with tamper-evident facts, into reproducible arguments. We build on AI FactSheets for instilling transparency and trustworthiness into the AI lifecycle and expand it in order to incorporate dynamic and nested facts, as well as complex model compositions in FL. Based on our approach, an auditor can validate, reproduce and certify a FL process. This can be directly applied in practice to address the challenges of AI engineering and ethics.

show abstract

Section: Objectives Of the Afˆ2 Frameworkmentioning

confidence: 99%

Section: Objectives Of the Afˆ2 Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach

Baracaldo¹,

Ali²,

Purcell³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Although research studied accountability in multiple domains, a generally acknowledged definition of accountability in the context of IBP is lacking [11][12][13][14], as extant research shows. Existing definitions are often bound to a particular context and focus on management or technology perspectives (cf.…”

Section: Accountability In the Context Of Ibpmentioning

confidence: 99%

“…e.g. [11][12][13][14]). Given this conceptual shortcoming, this paper addresses the research question: What is the scope of accountability facilitating to substantiate trust in the context of IBP?…”

Section: Introductionmentioning

confidence: 99%

Dimensions of Accountability in Inter-organizational Business Processes

Buchinger¹,

Kuhn²,

Balta³

2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Inter-organizational business processes are the basis of a globalized, highly dynamic, and digitalized world, enabling faster and cost-effective transactions. At the same time, they raise business vulnerabilities. A particular vulnerability is linked to the substantiation of trust between actors in dynamic business relationships, as trust affects interdependencies and complexity. An approach to address this vulnerability is the introduction of accountability mechanisms. Extant research suggests that accountability enables revealing causality and a transparent allocation of responsibilities for each process step. Thereby, corresponding actors can judge upon misbehavior and verify trust claims. Unfortunately, a thorough understanding of accountability and its dimensions accountability in the context of IBP is still missing. To address this gap, we develop a framework with dimensions of accountability. We demonstrate the resulting framework in an industrial supply chain case and derive implications for theory and practice.

show abstract

Accountability for Cyber- Physical Systems

Pretschner

Kacianka

2021

Encyclopedia of Cryptography, Security and Privacy

Self Cite

View full text Add to dashboard Cite

First and foremost I would like to thank my mother Andrea and my sister Nike for their unwavering support throughout my whole life and especially during the writing of this thesis. Thank you for lifting me up when I was down, for pushing me when I was lazy and for proof-reading every word I ever wrote.Next and most importantly, I want to thank my supervisor Alexander Pretschner.Through this joint journey, you taught me how to get to the point, to tell a good story, and to be a decent researcher and human being. You had my back when I did mess up and supported me when I tried something new. I am especially grateful for the honest and tough discussions -they made this text and all my work so much better. Thank you for shaping my view of science, good work, and my philosophy of life.A special thanks goes to all my colleagues past and present. You made the chair something I was looking forward to almost every single day. We made so many wonderful memories, shared stories and insights. All of you shaped my thinking and attitude and I am a better man for it. I am proud to have worked with you and grateful to be able to consider you friends. Thank you.Last, but not least, I want to thank my friends for their help, support and especially for the time not spent on the thesis. Anastasia, for making this last leg of my PhD so special; Celia, Eva, Evi, Hannes, Luis, Marci, Maresa, Michael, Peer, and Philip for those countless hikes and climbs that kept me sane; Niina and Jan for our project and the discussions that inspired me so much; Anne, Corinna, Luisa, Markus, and Nikolaus for those long nights and deep talks.

show abstract

Designing Accountable Systems

Cited by 24 publications

References 21 publications

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach

Dimensions of Accountability in Inter-organizational Business Processes

Accountability for Cyber- Physical Systems

Contact Info

Product

Resources

About