When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning

• URL: http://arxiv.org/abs/2609.08476v1
• Date: Tue, 08 Sep 2026 09:20:27 GMT
• Title: When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning
• Abstract summary: We show that Secure Aggregation (SA) is not a strong defense against model-update leakage in Federated Learning (FL)<n>We propose a lattice-based reconstruction approach that combines lattice reduction with structural filtering to reconstruct protected model states.<n>Our results show that colluding semi-honest nodes can recover the original local updates of honest nodes, enabling downstream reconstruction of private training data.
• Score: 18.50014823924619
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Secure Aggregation (SA) is widely regarded as a strong defense against model-update leakage in Federated Learning (FL), as it reveals only aggregate results while hiding individual updates. In Decentralized Federated Learning (DFL), SA is commonly instantiated as local neighborhood aggregation, where each node obtains a weighted aggregate over its neighbors. We show that this locality creates a structural leakage surface: sparse decentralized topologies provide colluding semi-honest nodes with asymmetric aggregate views, exposing multiple hidden linear combinations of honest participants' private states. Reconstructing private states from these aggregate views is fundamentally challenging, as both the private states and the aggregation coefficients are hidden. We tackle this challenge by establishing a formal connection to the Hidden Subset Sum Problem, a long-studied problem in cryptography. Building on this formulation, we design a lattice-based reconstruction approach that combines lattice reduction with structural filtering to reconstruct protected model states. We evaluate our attack on image, tabular, and text tasks under sparse DFL topologies. Our results show that colluding semi-honest nodes can recover the original local updates of honest nodes, enabling downstream reconstruction of private training data. These findings demonstrate that SA alone does not guarantee privacy in DFL when local aggregation induces asymmetric observations.

Related papers

• A Secure and Private Distributed Bayesian Federated Learning Design [56.92336577799572]
  Distributed Federated Learning (DFL) enables decentralized model training across large-scale systems without a central parameter server.<n>DFL faces three critical challenges: privacy leakage from honest-but-curious neighbors, slow convergence due to the lack of central coordination, and vulnerability to Byzantine adversaries aiming to degrade model accuracy.<n>We propose a novel DFL framework that integrates Byzantine robustness, privacy preservation, and convergence acceleration.
  arXiv  Detail & Related papers  (2026-02-23T16:12:02Z)
• Topological Federated Clustering via Gravitational Potential Fields under Local Differential Privacy [46.295754114458134]
  Existing one-shot methods rely on unstable pairwise centroid distances or neighborhood rankings.<n>We present Gravitational Federated Clustering (GFC), a novel approach to privacy-preserving federated clustering.<n>GFC transforms privatized client centroids into a global gravitational potential field.
  arXiv  Detail & Related papers  (2025-11-30T11:41:16Z)
• Breaking Privacy in Federated Clustering: Perfect Input Reconstruction via Temporal Correlations [15.144981031301512]
  Federated clustering allows multiple parties to discover patterns in distributed data without sharing raw samples.<n>Many protocols disclose intermediate centroids during training to reduce overhead.<n>We show that centroid disclosure in federated clustering significantly compromises privacy.
  arXiv  Detail & Related papers  (2025-11-10T13:06:16Z)
• Federated Learning Meets LLMs: Feature Extraction From Heterogeneous Clients [0.0]
  Federated learning (FL) enables collaborative model training without sharing raw data.<n>We propose FedLLM-Align, a framework that leverages pre-trained large language models (LLMs) as universal feature extractors.<n>We evaluate FedLLM-Align on coronary heart disease prediction using partitioned datasets with simulated schema divergence.
  arXiv  Detail & Related papers  (2025-09-29T14:06:52Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction [10.326927761316986]
  Federated clustering aims to discover global cluster structures across decentralized clients without sharing raw data.<n>There are two critical challenges: (1) privacy leakage during collaboration, and (2) robustness degradation due to aggregation of proxy information.<n>We propose Omni Federated Clustering, a unified and model-agnostic framework.
  arXiv  Detail & Related papers  (2025-05-19T13:04:59Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• Federated Deep Learning with Bayesian Privacy [28.99404058773532]
  Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. Homomorphic encryption (HE) based methods provide secure privacy protections but suffer from extremely high computational and communication overheads. Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity.
  arXiv  Detail & Related papers  (2021-09-27T12:48:40Z)
• Correlation Clustering Reconstruction in Semi-Adversarial Models [70.11015369368272]
  Correlation Clustering is an important clustering problem with many applications. We study the reconstruction version of this problem in which one is seeking to reconstruct a latent clustering corrupted by random noise and adversarial modifications.
  arXiv  Detail & Related papers  (2021-08-10T14:46:17Z)
• Unveiling the Potential of Structure-Preserving for Weakly Supervised Object Localization [71.79436685992128]
  We propose a two-stage approach, termed structure-preserving activation (SPA), towards fully leveraging the structure information incorporated in convolutional features for WSOL. In the first stage, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network. In the second stage, we propose a post-process approach, termed self-correlation map generating (SCG) module to obtain structure-preserving localization maps.
  arXiv  Detail & Related papers  (2021-03-08T03:04:14Z)

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.