---
title: 'FuSeFL: Secure Cross-Silo Federated Learning'
url: https://www.emergentmind.com/topics/fusefl
type: topic
---

# FuSeFL: Secure Cross-Silo Federated Learning

Searching arXiv for papers using the term “FuSeFL” and close variants to ground the article in the relevant literature.
FuSeFL is a polysemous research label rather than a single, stable technical term. In its exact expansion, it denotes **“Fully Secure and Scalable Cross-Silo Federated Learning”**, a federated learning scheme that decentralizes secure training across client pairs and confines the server’s role to secure aggregation [2507.13591]. Closely related spellings—**FuseFL**, **FUSE**, and **FUSE-Flow**—name distinct frameworks in one-shot federated learning, explainable fault localization, image–event monocular depth estimation, real-time multi-camera 3D reconstruction, cognitive theory, and spectral element discretization [2410.20380] [2403.10507] [2503.19739] [2606.04376] [2107.08268] [2306.06334]. The literature therefore uses the label in multiple unrelated senses, with the federated learning meaning being the exact expansion of the acronym “FuSeFL.”

## 1. Nomenclature and scope

The term appears in several recent arXiv papers with different expansions, objectives, and technical stacks. The exact string **FuSeFL** is attached to a secure cross-silo FL protocol, while nearby spellings such as **FuseFL** and **FUSE** refer to other systems.

| Label | Expansion or description | Source |
|---|---|---|
| FuSeFL | Fully Secure and Scalable Cross-Silo Federated Learning | [2507.13591] |
| FuseFL | One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion | [2410.20380] |
| FuseFL | Explainable fault localization with LLM prompting | [2403.10507] |
| FUSE | Label-Free Image-Event Joint Monocular Depth Estimation | [2503.19739] |
| FUSE-Flow | Decoupled framework for calibration and stateless real-time multi-view point cloud fusion | [2606.04376] |
| fuse | “fusion of activity-related sensory stimuli and awareness” | [2107.08268] |
| FUSE | Face Upwinded Spectral Element method | [2306.06334] |

This multiplicity is not merely typographic. Each work introduces a different formal object: a cryptographic FL protocol, a causal OFL method, an LLM-based debugging pipeline, a self-supervised multimodal depth estimator, a stateless 3D reconstruction framework, a cognitive construct, or a numerical PDE discretization. A common misconception is therefore to treat “FuSeFL” as a single framework that migrated across domains. The papers do not support that reading.

## 2. FuSeFL as “Fully Secure and Scalable Cross-Silo Federated Learning”

In the exact sense of the acronym, FuSeFL is a federated learning framework that **simultaneously secures client data, local updates, and the global model while eliminating the server-side training bottleneck**. It is designed for **cross-silo deployments** in which institutions operate under **strict privacy regulations (e.g., HIPAA, GDPR)**, have **large datasets**, and require confidentiality of both data and proprietary model parameters [2507.13591].

The motivating problem is twofold. First, existing secure FL methods trade security against efficiency: **homomorphic encryption (HE)** incurs **high computational and memory costs**; **differential privacy (DP)** degrades accuracy as the privacy budget tightens; and **secure multiparty computation (MPC)** protects inputs and updates without accuracy loss but sees its **communication overhead grow with client count**. Second, many methods leave the **global model in plaintext** on clients, which creates risks of **model theft or misuse (e.g., extraction, reverse engineering)**. FuSeFL addresses both issues by keeping the model secret-shared throughout training and by moving secure training away from the server.

Its architecture is pairwise and decentralized. **FuSeFL organizes clients into pairs per round**, performs **MPC-based training jointly within the pair over secret shares**, and uses **two non-colluding aggregation servers** for secure aggregation only. The server role is explicitly limited: **“The server’s role is strictly secure aggregation.”** The global model is secret-shared so that **no client or server ever holds the full global model in plaintext during training or aggregation**. The paper states the security goals as **data confidentiality**, **model confidentiality**, **update privacy**, and **integrity/correctness**, under an **honest-but-curious (semi-honest)** threat model with **no collusion assumed within a group per round** [2507.13591].

The cryptographic substrate is standard MPC. For additive secret sharing, a private value satisfies
$$
X = \sum [x]_j.
$$
For secure multiplication, FuSeFL uses **Beaver triples**:
$$
E_j = X_j - a_j,\qquad F_j = Y_j - b_j
$$
$$
E = \sum E_j,\qquad F = \sum F_j
$$
$$
Z_j = j \cdot E \cdot F + F \cdot a_j + E \cdot b_j + c_j.
$$
For non-linearities, it uses **function secret sharing (FSS)** with
$$
f(X) = f_1(X) + f_2(X).
$$
Federated aggregation is performed on shares only:
$$
[w_{t+1}]_s = \sum_{g=1}^{G} (n_g / n) [w_t^g]_s.
$$
The paper also defines **risk-aware dynamic grouping** as a **minimum-weight perfect matching**
$$
\mathcal{G}^* = \arg\min_{\mathcal{G} \subseteq \binom{C}{2}} \sum_{(C_i,C_j)\in\mathcal{G}} \rho(C_i, C_j),
$$
subject to each client appearing exactly once [2507.13591].

Two execution modes are described. In **FuSeFL-Serial**, a pair trains a single local model share sequentially on each partner’s data. In **FuSeFL-Parallel**, each client trains its own local model share and the pair performs **intra-pair secure aggregation** before sending shares to the two aggregation servers. The serial variant prioritizes accuracy; the parallel variant prioritizes latency and throughput.

Empirically, the reported setup uses **MNIST**, **Network-1 (3-layer MLP with ReLU)**, **Network-2 (2 conv + 2 FC with ReLU/max-pool)**, and **LeNet**, built on **AriaNN’s MPC training with two workers per group**. The paper reports that **FuSeFL-Serial reaches 97.20% (+0.8% over AriaNN-FL)** on Network-1, **matches AriaNN centralized secure training at 98.40%** on Network-2, and **matches AriaNN centralized at 99.20%** on LeNet. At scale, **with 128 clients, FuSeFL-Serial achieves up to 5.65× speedup over AriaNN-FL; FuSeFL-Parallel up to 7.83×**. For communication, the paper states that **for Network-1 with 10,000 clients and per-client dataset size 0.45 MB**, **AriaNN-FL total communication time ≈ 1,123 s**, whereas **FuSeFL total communication time ≈ 45.21 s**, which is **a 25× reduction (and up to 95% lower latency in large-scale regimes)**. Server memory is reduced by **≈ 50%**, since each server stores **(n/2) + 1** model instances rather than **n local model instances + 1 global** [2507.13591].

## 3. Federated-learning variants under the related label “FuseFL”

A second FL usage appears in **“FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion”** [2410.20380]. This paper does not address secure MPC or model confidentiality. Instead, it addresses **One-shot Federated Learning (OFL)**, where each client trains locally and communicates only once. Its central diagnosis is the **isolation problem**: under **non-IID data**, isolated local models in OFL can fit **spurious correlations** rather than invariant features.

The method is built from **blockwise network decomposition** and **bottom-up progressive training and fusion**. A network is decomposed as
$$
F = \Lambda \circ H^K \circ H^{K-1} \circ \cdots \circ H^1,
$$
and FuseFL progressively trains and fuses blocks from low to high. The feature-level fusion operator is
$$
fus_k(x) = \{ H_1^k(x), H_2^k(x), \dots, H_M^k(x) \},
$$
followed by either an **Averaging adaptor**
$$
A_{\mathrm{avg}}(x) = \mathrm{Average}(fus_k(x))
$$
or a **1×1 convolution adaptor**
$$
A_{\mathrm{conv}}(x) = \mathrm{Conv}_{1\times1}(\mathrm{Concat}(fus_k(x))).
$$
The paper emphasizes that this introduces **“no additional communication costs”** relative to OFL because **summing across \(K\) rounds equals \(S\) per client** [2410.20380].

Its empirical claims are framed as accuracy and storage trade-offs. On **CIFAR-10**, the paper reports **FuseFL K=4: 73.79/84.58/81.15** for \(\alpha=0.1/0.3/0.5\), and **K=2: 70.85/81.41/84.34**. On **SVHN**, it reports **K=2: 76.88/91.07/90.87**, **K=4: 78.08/89.63/89.34**, and **K=8: 80.31/88.88/89.94**. The paper also states that **FuseFL supports high scalability of clients, heterogeneous model training, and low memory costs**, and that it is **“the first attempt using causality to analyze and alleviate data heterogeneity of OFL”** [2410.20380].

The relation between the two FL papers is purely nominal. FuSeFL [2507.13591] is a **fully secure and scalable FL scheme designed for cross-silo settings**; FuseFL [2410.20380] is a **one-shot** accuracy-improvement method centered on **causal feature augmentation and progressive model fusion**. They solve different problems and rely on different assumptions.

## 4. FuseFL in explainable fault localization

A third usage appears in software engineering. **FuseFL** in **“Demystifying Faulty Code with LLM: Step-by-Step Reasoning for Explainable Fault Localization”** is an **LLM-assisted, explainable fault localization approach** that fuses **spectrum-based suspiciousness**, **test-case execution outcomes**, and a **description of intended code functionality** into a structured prompt [2403.10507].

The method is a prompt-fusion pipeline rather than a numerical fusion algorithm. It first executes tests with **coverage instrumentation**, computes **SBFL suspiciousness scores** per line, extracts **inputs and expected outputs** from assert-style tests, records **actual outputs or runtime errors**, and then prompts **ChatGPT, GPT-3.5 as of Sept-11-2023** using **Zero-shot Chain-of-Thought prompting** with **“Let’s think step by step.”** The suspiciousness formulas explicitly listed in the paper include **Ochiai**, **Tarantula**, **DStar**, **Barinel**, and **OP2**; for example,
$$
Ochiai(l) = \frac{n_f(l)}{\sqrt{n_f \cdot \left(n_f(l) + n_p(l)\right)}}.
$$
The prompt includes the **top 5 lines** by suspiciousness [2403.10507].

The evaluation uses a **curated subset of the Refactory dataset** with **324 faulty Python codes**, **600 faulty lines**, and a new human-authored explanation set. The paper reports **Top-1 localized faults** of **89** for Tarantula, **117** for Ochiai, **115** for OP2, **89** for Barinel, **115** for DStar, **149** for XAI4FL, and **197** for FuSeFL. It further states **“a more than 30% increase in the number of successfully localized faults at Top-1 compared to the baseline”** and **“FuSeFL vs XAI4FL: +32.3% at Top-1.”** For explanation quality, the paper created **human explanations for 600 faulty lines** and reports that **for 22 out of the 30 randomly sampled cases, FuseFL generated correct explanations** [2403.10507].

This usage differs from both FL meanings. The shared term “fusion” here refers to combining debugging signals in a prompt, not to secure aggregation, pairwise MPC, or progressive feature fusion in OFL.

## 5. Multimodal perception and 3D reconstruction uses of FUSE

The term is also used in perception and 3D reconstruction, again with different semantics. In **“FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion,”** FUSE is a **label-free (self-supervised) image–event framework** for monocular depth estimation [2503.19739]. The paper identifies two barriers: **limited annotated image–event–depth datasets** and **frequency mismatch between modalities**. Its solution combines **Parameter-efficient Self-supervised Transfer (PST)** and **Frequency-Decoupled Fusion (FreDFuse)**.

PST is a **two-stage, lightweight transfer** that aligns an event encoder’s latent space with an image depth foundation model such as **DepthAnything V2**. Stage I updates only **LoRA and PatchEmbed** in the event encoder, reported as **about 1.8% of the encoder’s parameters**. Stage II freezes the encoders and trains only **FreDFuse** on **randomly degraded image–event inputs**. The alignment loss is
$$
L_{\text{align}} = L_1(d, d^*) + L_{\cos}(F, F^*),
$$
with a cosine-gated latent term and the similarity band **\((\alpha = 0.2, \beta = 0.85)\)**. Events are voxelized into \(V \in \mathbb{R}^{H \times W \times B}\) with **the paper uses \(B=3\)** [2503.19739].

FreDFuse explicitly separates **high-frequency components (edges, motion dynamics)** from **low-frequency components (global structure, smooth surfaces)** using **Gaussian–Laplacian pyramids**, then performs **modality-guided cross-attention** in which **the event branch dominates high-frequency fusion, and the image branch dominates low-frequency fusion**. The paper reports **state-of-the-art performance with 14% and 24.9% improvements in Abs.Rel on MVSEC and DENSE datasets**, **FreDFuse (vs. vanilla cross-attention) cuts Abs.Rel by ~8%**, and **PST reduces trainable parameters by >80% while improving average performance by ~19.7% across metrics** [2503.19739].

A separate but related usage appears in **“FUSE-Flow: A Decoupled Framework for Calibration and Stateless Real-Time Multi-View Point Cloud Fusion”** [2606.04376]. FUSE-Flow comprises **GMAC (Geometry-aligned Multi-view extrinsic calibration)** and **FUSE (Reliability-guided multi-view point cloud fusion)**. The framework is explicitly **decoupled** and **stateless**: no **TSDF volume**, **SLAM pose graph**, or **bundle adjustment** is maintained. GMAC performs **metric lifting** of transformer-predicted poses using **Depth-guided Reprojection Consistency (RC)** and **Cycle Consistency (CC)**; FUSE uses **Measurement Confidence Modeling (MCM)**, **Cross-View Geometric Consistency (CVGC)**, and **Adaptive Spatial Hashing (ASH)**.

The calibration objective is written as
$$
L_{\text{scale}}(s) = \sum_{(i,j)\in E} \sum_{u\in U_{ij}} W_{ij}(u) |Z_{ij}(u, s) - D_j(x_{ij})|^2,
$$
with the closed-form scale estimator
$$
s^* = \frac{\sum W_{ij}(u) (d_{ij}(u) - b_{ij}(u)) a_{ij}(u)}{\sum W_{ij}(u) a_{ij}(u)^2}.
$$
The fusion weights use the harmonic mean
$$
w(x) = \frac{2 c(x) \omega_{\text{geo}}(x)}{c(x) + \omega_{\text{geo}}(x) + \epsilon}.
$$
The paper reports that **FUSE achieves 26.3–43.1 FPS across 2–8 cameras at 640×480 on an RTX 4090**, uses **1.9–3.1 GB GPU**, and that **R3D3 runs at 5.8–11.2 FPS** with **6.4–10.1 GB** for comparable settings. For calibration, **VGGT 1.04° → 0.63°, 4.61 mm → 3.07 mm** on ScanNet is reported as the **best absolute** among the listed backbones [2606.04376].

These FUSE systems are unrelated to FuSeFL in federated learning, but they illustrate how the same or adjacent acronymic forms recur in multimodal fusion problems.

## 6. Cognitive and numerical-scientific uses

The word **fuse** in **“From Flow to Fuse: A Cognitive Perspective”** is not an acronym. It is introduced as a new construct defined as the **“fusion of activity-related sensory stimuli and awareness”** [2107.08268]. The paper argues that the prevalent notion of flow is conceptually vague, especially around the phrase **“merging of action and awareness.”** Fuse narrows the phenomenology to episodes in which consciousness is filled exclusively with **activity-related sensory stimuli**, while **planning, model-building, mental simulation, conscious comparison of alternatives** do not enter awareness.

The paper’s preliminary model is built around **working memory (WM)**, **attention**, **saliency**, **automaticity**, **mind wandering/DMN**, and **cognitive load**. It specifies a **requirement**—**Effortless attention focused on activity-related sensory stimuli**—and three **corequisites**: **Effortless avoidance of activity-related thoughts**, **Effortless avoidance of activity-unrelated thoughts**, and **Effortless avoidance of activity-unrelated sensory stimuli**. It then derives design heuristics such as **Minimize time between actions**, **Minimize relatability**, **Leverage sound design**, **Help individuals meet their OCLs**, **Optimize complexity, not difficulty**, and **Facilitate learning with predictable systems** [2107.08268].

In numerical analysis, **FUSE** names the **Face Upwinded Spectral Element method** [2306.06334]. The paper introduces a **high-order, linearly stable discretization on unstructured quadrilateral meshes** that **keeps the solution field continuous (CG-like) while incorporating upwind stabilization only on face nodes**. The key node placement is **the Gauss–Legendre quadrature nodes plus endpoints (“GL+E”)**. The paper states that **equidistant or Gauss–Lobatto nodes lead to instability for \(p \ge 3\)**, whereas **GL+E nodes yield a stable upwind operator (verified numerically up to \(p = 20\))**. For the semi-discrete 1D advection system, stability is characterized by **\(\mathrm{Re}(\lambda) \ge 0\)** for all eigenvalues of the derivative operator. The method is demonstrated on **convection-dominated flows, Poisson’s equation, and the incompressible Navier–Stokes equations**, with empirical convergence **between orders \(p\) and \(p+1\)** [2306.06334].

The paper explicitly notes a terminological caveat: **“The name ‘FuSeFL’ does not appear in the paper; we treat ‘FuSeFL’ as referring to the same Face Upwinded Spectral Element approach described therein.”** That statement is important because it shows that, in some discussions, the label is being extended beyond the authors’ own nomenclature.

## 7. Sources of ambiguity and comparative interpretation

Across the cited works, the label family **FuSeFL / FuseFL / FUSE / FUSE-Flow / fuse** spans at least four distinct patterns. First, there are **federated learning** uses: secure cross-silo training with secret sharing and MPC [2507.13591], and one-shot FL with progressive blockwise model fusion [2410.20380]. Second, there are **signal-fusion** and **multimodal perception** uses: prompt-level fusion for fault localization [2403.10507], frequency-decoupled image–event fusion [2503.19739], and reliability-guided multi-view point cloud fusion [2606.04376]. Third, there is the **cognitive** use of fuse as a phenomenological construct [2107.08268]. Fourth, there is the **numerical PDE** use of FUSE as a face-upwinded discretization [2306.06334].

This suggests that acronym reuse is often driven by the mnemonic appeal of **fuse/fusion**, but the technical content is not shared across papers. That generalization is strongest for [2410.20380], [2403.10507], [2503.19739], and [2606.04376], all of which explicitly describe some form of fusion. A plausible implication is that the proximity of these labels increases the risk of bibliographic or conceptual confusion, especially because the exact string **FuSeFL** has a specific meaning in [2507.13591] but is also used informally in summaries of unrelated work.

For precision, the term should therefore be disambiguated by domain. In federated learning, **FuSeFL** most precisely denotes **Fully Secure and Scalable Cross-Silo Federated Learning** [2507.13591]. In one-shot FL, **FuseFL** denotes **progressive model fusion** for causal feature augmentation [2410.20380]. In software engineering, **FuseFL** denotes an **LLM-assisted explainable fault localization** method [2403.10507]. In perception and reconstruction, **FUSE** and **FUSE-Flow** denote multimodal fusion systems [2503.19739] [2606.04376]. In cognitive theory, **fuse** denotes a redefinition of a class of sensory-bound experiences [2107.08268]. In numerical analysis, **FUSE** denotes the **Face Upwinded Spectral Element** method [2306.06334].

Source: https://www.emergentmind.com/topics/fusefl