mlsanityData to 14 Oct 2026

Which PPML Would a User Choose? A Structured Decision Support Framework for Developers to Rank PPML Techniques Based on User Acceptance Criteria

arXiv 2411.06995 ↗First posted 11 Nov 2024cs.AI cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Using Privacy-Enhancing Technologies (PETs) for machine learning often influences the characteristics of a machine learning approach, e.g., the needed computational power, timing of the answers or how the data can be utilized. When designing a new service, the developer faces the problem that some decisions require a trade-off. For example, the use of a PET may cause a delay in the responses or adding noise to the data to improve the users' privacy might have a negative impact on the accuracy of the machine learning approach. As of now, there is no structured way how the users' perception of a machine learning based service can contribute to the selection of Privacy Preserving Machine Learning (PPML) methods. This is especially a challenge since one cannot assume that users have a deep technical understanding of these technologies. Therefore, they can only be asked about certain attributes that they can perceive when using the service and not directly which PPML they prefer. This study introduces a decision support framework with the aim of supporting the selection of PPML technologies based on user preferences. Based on prior work analysing User Acceptance Criteria (UAC), we translate these criteria into differentiating characteristics for various PPML techniques. As a final result, we achieve a technology ranking based on the User Acceptance Criteria while providing technology insights for the developers. We demonstrate its application using the use case of classifying privacy-relevant information. Our contribution consists of the decision support framework which consists of a process to connect PPML technologies with UAC, a process for evaluating the characteristics that separate PPML techniques, and a ranking method to evaluate the best PPML technique for the use case.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 81 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

14 of 81 references.

References · 14

  1. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  2. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 85
  3. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  4. 2021Federated Learning Meets Natural Language Processing: A Surveycited by 43
  5. 2020A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metriccited by 42
  6. 2021Benchmarking Differential Privacy and Federated Learning for BERT Modelscited by 28
  7. 2021Privacy enabled Financial Text Classification using Differential Privacy and Federated Learningcited by 18
  8. 2022Differential Privacy in Natural Language Processing: The Story So Farcited by 12
  9. 2022Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryptioncited by 9
  10. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 9
  11. 2021When Differential Privacy Meets Interpretability: A Case Studycited by 8
  12. 2020Evaluation of Federated Learning in Phishing Email Detectioncited by 6
2 more
  1. 2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
  2. 2022MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inferencecited by 4

Built on by

Not cited yet.