The clash between the transparency demands of tax

The gap

Evidence profile

Sourced from the future-work section and limitations and future work and stated research gap and stated challenges of the source papers, classified as general, spanning 6 journals.

Supporting evidence — 8 representative gaps

• Federated Learning Paradigms for Privacy-Preserving Multi Organizational Threat Intelligence Sharing (2026) · Iconic Research and Engineering Journals · doi

  Developing more robust and scalable federated learning paradigms. Investigating the application of federated learning to other domains, such as finance, healthcare, and telecommunications. Exploring the use of hybrid, auditable, and trust-aware architectures to balance privacy, analytical utility, and operational resilience.

  generalfuture-work section
  Keywords: developing robust scalable federated learning paradigms investigating application
• Exploiting explanations for model extraction via knowledge distillation and mitigation with private counterfactuals (2026) · Frontiers in Artificial Intelligence · doi

  We discuss the contribution, limitations of our current approach and potential future research directions: • Attack Scope: This work is limited to MEA that exploit CFs. Other types of privacy attacks, such as MIA and inversion, are not examined in this paper and therefore fall outside the scope of our current analysis. A future direction is to evaluate whether the proposed mitigation strategy remains effective against this broader class of privacy attacks. • Privacy-Performance Trade-off: Integrating DP into the CF generator mitigates MEA, but it also introduces limitations including proximity, by degrading explanation quality, prediction gain, and plausibility in some cases. As future work, a more systematic study of the privacy-utility trade-off is needed, including evaluating a wider range of privacy budgets and optimization settings for the DP-based CF generator to better balance protection and explanation quality. • Focus on Deep Learning Applications: This work focuses on MEA for DNNs, where knowledge distillation is particularly effective due to the expressive capacity of DNNs and their ability to learn rich data representations. This focus limits the applicability of our findings to other model families, such as traditional baselines including tree-based or ensemble Frontiers in Artificial Intelligence 15 frontiersin.org Ezzeddine et al. 10.3389/frai.2026.1746910 methods. Since KD proved effective in the DNN setting, a natural future direction is to explore how KD-based extraction strategies can be adapted to non-DNN algorithms and whether similar performance gains can be achieved.

  generallimitationsevidence 5/5
  Keywords: privacy future ective including based limitations current scope attacks direction whether performance trade generator explanation
• SecureFedShield: An Adaptive Privacy-Preserving Federated Defense Framework Against Adversarial Attacks in Financial Fraud Detection (2026) · International Journal of Creative and Open Research in Engineering and Management · doi

  References This paper presented SecureFedShield, an adaptive privacy-preserving federated learning framework for secure financial fraud detection under adversarial environments. The proposed framework integrates adaptive privacy protection, continuous trust-based client evaluation, adversarial update detection, and a unified aggregation trust-aware collaborative learning architecture. Unlike conventional federated independently address privacy preservation or adversarial robustness, complementary SecureFedShield mechanisms to enhance both model security and predictive performance. learning approaches combines robust these into that [1] H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, "Communication- Efficient Learning of Deep Networks from Decentralized Data," in Proc. 20th Int. Conf. Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, USA, 2017, pp. 1273–1282. [2] C. Dwork, "Differential Privacy," in Proc. 33rd Int. Colloquium on Automata, Languages and Programming (ICALP), Venice, Italy, 2006, pp. 1–12. © 2026 The Author(s). Published by IJCOPE Journal. Website: https://ijcope.org/ 16 International Journal of Creative and Open Research in Engineering and Management ISSN: 3108-1754 (Online) Volume 02 Issue 08 Augustl-2026 | Impact Factor: 3.5 [3] C. Dwork and A. Roth, The Algorithmic Foundations of Differential Privacy. Boston, MA, USA: Now Publishers Inc., 2014. [4] P. Kairouz et al., "Advances and Open Problems in Federated Learning," Foundations and Trends® in Machine Learning, vol. 14, no. 1–2, pp. 1–210, 2021. [5] K. Bonawitz et al., "Practical Secure Aggregation for Privacy-Preserving Machine Learning," in Proc. ACM SIGSAC Conf. Computer and Communications Security (CCS), Dallas, TX, USA, 2017, pp. 1175– 1191. [6] B. Hitaj, G. Ateniese, and F. Perez-Cruz, "Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning," in Proc. ACM SIGSAC Conf. Computer and Communications Security (CCS), Dallas, TX, USA, 2017, pp. 603–618. [7] M. Nasr, R. Shokri, and A. Houmansadr, "Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-Box Inference Attacks against Centralized and Federated Learning," in Proc. IEEE Symp. Security and Privacy (SP), San Francisco, CA, USA, 2019, pp. 739–753. [8] L. Zhu, Z. Liu, and S. Han, "Deep Leakage from Gradients," in Advances in Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada, 2019. [9] J. Geiping, H. Bauermeister, H. Dröge, and M. Moeller, "Inverting Gradients – How Easy Is It to Break Privacy in Federated Learning?" in Advances in Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada, 2020. [10] L. Melis, C. Song, E. De Cristof

  generalfuture workevidence 5/5
  Keywords: learning privacy federated deep proc security adversarial conf advances information securefedshield adaptive preserving framework secure
• Federated learning for privacy protection of connected autonomous vehicles in multi-access edge computing networks (2026) · Discover Artificial Intelligence · doi

  Traditional federated learning is ill-suited to dynamic topology changes, resulting in privacy leaks and data association attacks. There is a need for a federated learning framework that achieves a balance between privacy protection, robustness, and efficiency in dynamic multi-access environments.

  generalstated research gapevidence 5/5
  Keywords: traditional federated learning ill-suited dynamic topology changes resulting
• Fedagentshield: An Adaptive Federated Reinforcement Learning Framework for Privacy-Preserving Autonomous Cyber Defence (2026) · International Journal of Computer Information Systems and Industrial Management Applications · doi

  Existing Federated Reinforcement Learning approaches predominantly employ conventional aggregation strategies. The integration of Federated Learning and Reinforcement Learning via Federated Reinforcement Learning offers a promising approach to privacy-preserving distributed cyber defence. Important client performance indicators are not incorporated into the global policy aggregation process.

  generalstated research gapevidence 5/5
  Keywords: existing federated reinforcement learning approaches predominantly employ conventional
• SecureFedShield: An Adaptive Privacy-Preserving Federated Defense Framework Against Adversarial Attacks in Financial Fraud Detection (2026) · International Journal of Creative and Open Research in Engineering and Management · doi

  Existing research has primarily focused on addressing individual aspects of secure federated learning, rather than providing a unified framework. Differential Privacy mechanisms do not distinguish between trustworthy and potentially malicious participants. There is a need for a federated learning framework that integrates adaptive privacy preservation, continuous client trust assessment, adversarial update detection, and robust aggregation.

  generalstated research gapevidence 5/5
  Keywords: existing research has primarily focused addressing individual aspects
• TrustScale ML Verifiable Privacy Preserving Multi Node Training for Robust Model Development (2026) · International Journal of Intelligent Systems and Data Science · doi

  This paper presented TrustScale ML, a comprehensive framework for verifiable, privacy-preserving distributed machine learning integrating PoL with homomorphic encryption. The framework supports diverse learning patterns while providing computation integrity verification, gradient confidentiality, and Byzantine resilience. Returning to our research questions: (RQ1) PoL provides computation integrity verification; (RQ2) HE provides confidentiality during transmission and aggregation; (RQ3) overhead is quantified in experimental results; (RQ4) Byzantine resilience is provided through robust aggregation; and (RQ5) the framework scales with sub-linear verification overhead growth. Future work includes: (1) more efficient cryptographic constructions, (2) adaptive security policies, (3) support for federated and split learning, (4) verification for reinforcement learning and GANs, (5) trusted execution environment integration, and (6) formal verification methods and security certifications.

  generalfuture workevidence 5/5
  Keywords: verification learning framework computation integrity confidentiality byzantine resilience provides aggregation overhead security presented trustscale comprehensive
• Privacy preserving and auditable tax fraud detection using zero knowledge transformer inference (2026) · Discover Artificial Intelligence · doi

  The clash between the transparency demands of tax authorities and taxpayers' need for the minimisation of data and the protection of privacy. The need for a scalable and auditable solution for tax fraud detection. The challenge of integrating modern deep learning with cryptographic verification.

  generalstated challengesevidence 5/5
  Keywords: clash between transparency demands tax authorities taxpayers need

Questions about this gap