Reviving Purpose Limitation and Data Minimisation in Personalisation, Profiling and Decision-Making Systems

• URL: http://arxiv.org/abs/2101.06203v1
• Date: Fri, 15 Jan 2021 16:36:29 GMT
• Title: Reviving Purpose Limitation and Data Minimisation in Personalisation, Profiling and Decision-Making Systems
• Authors: Mich\`ele Finck and Asia Biega
• Abstract summary: This paper determines, through an interdisciplinary law and computer science lens, whether data minimisation and purpose limitation can be meaningfully implemented in data-driven systems. Our analysis reveals that the two legal principles continue to play an important role in mitigating the risks of personal data processing. We highlight that even though these principles are important safeguards in the systems under consideration, there are important limits to their practical implementation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper determines, through an interdisciplinary law and computer science lens, whether data minimisation and purpose limitation can be meaningfully implemented in data-driven algorithmic systems, including personalisation, profiling and decision-making systems. Our analysis reveals that the two legal principles continue to play an important role in mitigating the risks of personal data processing, allowing us to rebut claims that they have become obsolete. The paper goes beyond this finding, however. We highlight that even though these principles are important safeguards in the systems under consideration, there are important limits to their practical implementation, namely, (i) the difficulties of measuring law and the resulting open computational research questions as well as a lack of concrete guidelines for practitioners; (ii) the unacknowledged trade-offs between various GDPR principles, notably between data minimisation on the one hand and accuracy or fairness on the other; (iii) the lack of practical means of removing personal data from trained models in order to ensure legal compliance; and (iv) the insufficient enforcement of data protection law.

Related papers

• The trade-off between data minimization and fairness in collaborative filtering [1.8936798735951967]
  General Data Protection Regulations aim to safeguard individuals' personal information from harm. While full compliance is mandatory in the EU, it is not in other places. This paper studies the relationship between principles of data minimization and fairness in recommender systems.
  arXiv  Detail & Related papers  (2024-09-21T02:32:26Z)
• An evidence-based methodology for human rights impact assessment (HRIA) in the development of AI data-intensive systems [49.1574468325115]
  We show that human rights already underpin the decisions in the field of data use. This work presents a methodology and a model for a Human Rights Impact Assessment (HRIA) The proposed methodology is tested in concrete case-studies to prove its feasibility and effectiveness.
  arXiv  Detail & Related papers  (2024-07-30T16:27:52Z)
• The Data Minimization Principle in Machine Learning [61.17813282782266]
  Data minimization aims to reduce the amount of data collected, processed or retained. It has been endorsed by various global data protection regulations. However, its practical implementation remains a challenge due to the lack of a rigorous formulation.
  arXiv  Detail & Related papers  (2024-05-29T19:40:27Z)
• Lazy Data Practices Harm Fairness Research [49.02318458244464]
  We present a comprehensive analysis of fair ML datasets, demonstrating how unreflective practices hinder the reach and reliability of algorithmic fairness findings. Our analyses identify three main areas of concern: (1) a textbflack of representation for certain protected attributes in both data and evaluations; (2) the widespread textbf of minorities during data preprocessing; and (3) textbfopaque data processing threatening the generalization of fairness research. This study underscores the need for a critical reevaluation of data practices in fair ML and offers directions to improve both the sourcing and usage of datasets.
  arXiv  Detail & Related papers  (2024-04-26T09:51:24Z)
• Distributed Machine Learning and the Semblance of Trust [66.1227776348216]
  Federated Learning (FL) allows the data owner to maintain data governance and perform model training locally without having to share their data. FL and related techniques are often described as privacy-preserving. We explain why this term is not appropriate and outline the risks associated with over-reliance on protocols that were not designed with formal definitions of privacy in mind.
  arXiv  Detail & Related papers  (2021-12-21T08:44:05Z)
• Learning to Limit Data Collection via Scaling Laws: Data Minimization Compliance in Practice [62.44110411199835]
  We build on literature in machine learning law to propose framework for limiting collection based on data interpretation that ties data to system performance. We formalize a data minimization criterion based on performance curve derivatives and provide an effective and interpretable piecewise power law technique.
  arXiv  Detail & Related papers  (2021-07-16T19:59:01Z)
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective [10.901568085406753]
  Article is dedicated to surveying on the state-of-the-art privacy techniques, which can be employed in Federated learning. Recent research has demonstrated that retaining data and on computation in FL is not enough for privacy-guarantee. This is because ML model parameters exchanged between parties in an FL system, which can be exploited in some privacy attacks.
  arXiv  Detail & Related papers  (2020-11-10T21:41:25Z)
• Operationalizing the Legal Principle of Data Minimization for Personalization [64.0027026050706]
  We identify a lack of a homogeneous interpretation of the data minimization principle and explore two operational definitions applicable in the context of personalization. We find that the performance decrease incurred by data minimization might not be substantial, but it might disparately impact different users.
  arXiv  Detail & Related papers  (2020-05-28T00:43:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.