mlsanityData to 7 Oct 2026

From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learning

arXiv 2512.15460 ↗First posted 17 Dec 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Data Reconstruction Attacks (DRA) pose a significant threat to Federated Learning (FL) systems by enabling adversaries to infer sensitive training data from local clients. Despite extensive research, the question of how to characterize and assess the risk of DRAs in FL systems remains unresolved due to the lack of a theoretically-grounded risk quantification framework. In this work, we address this gap by introducing Invertibility Loss (InvLoss) to quantify the maximum achievable effectiveness of DRAs for a given data instance and FL model. We derive a tight and computable upper bound for InvLoss and explore its implications from three perspectives. First, we show that DRA risk is governed by the spectral properties of the Jacobian matrix of exchanged model updates or feature embeddings, providing a unified explanation for the effectiveness of defense methods. Second, we develop InvRE, an InvLoss-based DRA risk estimator that offers attack method-agnostic, comprehensive risk evaluation across data instances and model architectures. Third, we propose two adaptive noise perturbation defenses that enhance FL privacy without harming classification accuracy. Extensive experiments on real-world datasets validate our framework, demonstrating its potential for systematic DRA risk evaluation and mitigation in FL systems.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 36 of its 56 references that are in the map. First posted on arXiv 17 Dec 2025.

Builds on

36 of 56 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2019Deep Leakage from Gradientscited by 1,004
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  8. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  9. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  10. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  11. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  12. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
24 more
  1. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  2. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  3. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 104
  4. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  5. 2022Membership Inference Attacks by Exploiting Loss Trajectorycited by 93
  6. 2020Acceleration for Compressed Gradient Descent in Distributed and Federated Optimizationcited by 90
  7. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 79
  8. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  9. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  10. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
  11. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  12. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 35
  13. 2022SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compressioncited by 34
  14. 2020When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Controlcited by 32
  15. 2021Measuring Data Leakage in Machine-Learning Models with Fisher Informationcited by 31
  16. 2020A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimizationcited by 27
  17. 20223PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregationcited by 27
  18. 2020An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategiescited by 18
  19. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 18
  20. 2021Faster Rates for Compressed Federated Learning with Client-Variance Reductioncited by 14
  21. 2022Coresets for Vertical Federated Learning: Regularized Linear Regression and K-Means Clusteringcited by 14
  22. 2024Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attackscited by 13
  23. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  24. 2024Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approachcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Modelscited by 1
  2. 2026Revisiting Label Inference Attacks in Vertical Federated Learning: Why They Are Vulnerable and How to Defendcited by 0
  3. 2026CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learningcited by 0