The Capacity of Information-Theoretic Secure Aggregation in Federated Learning
- URL: http://arxiv.org/abs/2606.07277v1
- Date: Fri, 05 Jun 2026 13:53:27 GMT
- Title: The Capacity of Information-Theoretic Secure Aggregation in Federated Learning
- Abstract summary: We study the $T$-colluding information-theoretic secure aggregation problem with $N$ users.<n>Unlike prior work, we model key distribution through user-to-user communication.<n>We show that the optimal performance can be achieved using only pairwise shared keys.
- Score: 38.64656884737012
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Secure aggregation allows a server to aggregate users' local updates while preserving update privacy. Existing information-theoretic problems typically assume that correlated random keys are provided by a trusted third party (TTP) or generated via prescribed groupwise structures, while the communication cost for establishing such correlated keys is often ignored. Consequently, the fundamental limits under general key-distribution mechanisms remain unknown. In this paper, we study the $T$-colluding information-theoretic secure aggregation problem with $N$ users under a general two-phase framework consisting of a key distribution phase and an update aggregation phase. Unlike prior work, we model key distribution through user-to-user communication and allow arbitrary user-generated key-distribution mechanisms, eliminating TTP or prescribed structures. This enables a joint characterization of three resources: randomness for security, key-distribution communication, and aggregation communication. We completely characterize the capacity region among these three resources by constructing a novel secure aggregation scheme together with a matching information-theoretic converse. In particular, we develop an explicit deterministic capacity-achieving construction over any finite field of size at least $N$, whereas most existing schemes either rely on TTP or employ randomized or existential constructions over sufficiently large finite fields. We further show that the optimal performance can be achieved using only pairwise shared keys, enabling implementation via Diffie--Hellman key exchange. Compared with Google's seminal secure aggregation scheme, the proposed scheme requires fewer random masking keys while preserving the same aggregation communication overhead.
Related papers
- Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation [45.381652768314375]
Homomorphic Encryption naturally fits the client--aggregator communication pattern of Federated Learning.<n>We propose lightweight multi-secret-key protocols for private average aggregation based on RLWE-based Homomorphic Encryption.<n>Our results show that the proposed approach substantially reduces ciphertext expansion and online cost, while preserving practical homomorphic aggregation performance.
arXiv Detail & Related papers (2026-09-01T23:21:48Z) - Information-Theoretic Decentralized Secure Aggregation with Collusion Resilience [95.33295072401832]
We study the problem of decentralized secure aggregation (DSA) from an information-theoretic perspective.<n>We characterize the optimal rate region, which specifies the minimum achievable communication and secret key rates for DSA.<n>Our results establish the fundamental performance limits of DSA, providing insights for the design of provably secure and communication-efficient protocols.
arXiv Detail & Related papers (2025-08-01T12:51:37Z) - Collusion-Resilient Hierarchical Secure Aggregation with Heterogeneous Security Constraints [42.80769898523078]
Motivated by federated learning (FL), secure aggregation aims to securely compute, as efficiently as possible, the sum of a set of inputs distributed across many users.<n>We study weakly-secure HSA (WS-HSA) with collusion resilience.<n>We characterize the optimal total key rate, i.e., the total number of independent key symbols required to ensure both server and relay security.
arXiv Detail & Related papers (2025-07-19T23:09:57Z) - Multiplication triples from entangled quantum resources [3.2074558838636262]
An efficient paradigm for multi-party computation (MPC) are protocols structured around access to shared pre-processed computational resources.<n>We present a novel approach for generating these correlations from entangled quantum graph states.<n>We prove perfect privacy for our protocol, assuming access to an ideal copy of the resource state.
arXiv Detail & Related papers (2025-05-15T15:06:32Z) - Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Association [93.46811590752814]
Hierarchical secure aggregation is motivated by federated learning (FL)<n>In this paper, we consider HSA with a cyclic association pattern where each user is connected to $B$ consecutive relays.<n>We propose an efficient aggregation scheme which includes a message design for the inputs inspired by gradient coding.
arXiv Detail & Related papers (2025-03-06T15:53:37Z) - PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning [49.916365792036636]
Federated learning (FL) has recently gained significant momentum due to its potential to leverage large-scale distributed user data.<n>The transmitted model updates can potentially leak sensitive user information, and the lack of central control of the local training process leaves the global model susceptible to malicious manipulations on model updates.<n>We develop a general framework PriRoAgg, utilizing Lagrange coded computing and distributed zero-knowledge proof, to execute a wide range of robust aggregation algorithms while satisfying aggregated privacy.
arXiv Detail & Related papers (2024-07-12T03:18:08Z) - Coding-Based Hybrid Post-Quantum Cryptosystem for Non-Uniform Information [53.85237314348328]
We introduce for non-uniform messages a novel hybrid universal network coding cryptosystem (NU-HUNCC)
We show that NU-HUNCC is information-theoretic individually secured against an eavesdropper with access to any subset of the links.
arXiv Detail & Related papers (2024-02-13T12:12:39Z) - Sharing classical secrets with continuous-variable entanglement:
Composable security and network coding advantage [0.913755431537592]
We show that multi-partite entangled resources achieve a genuine advantage over point-to-point protocols for quantum communication.
This is the first concrete compelling examples of multi-partite entangled resources achieving a genuine advantage over point-to-point protocols for quantum communication.
arXiv Detail & Related papers (2021-04-21T17:37:28Z)
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.