arXiv cs.AI· Andreas Sendros, Nikolaos Pavlidis, Vasilios Perifanis, Pavlos S. Efraimidis·· 3 小时前AI 评分42
联邦学习代币化奖励系统：隐私与公平的权衡
Tokenized Reward Systems for Federated Learning: The Privacy vs. Fairness Tradeoff
AI 导读
一项 arXiv 论文设计并评估了两个用于联邦学习奖励分配的 Solidity 智能合约：一个按公开质量分数比例分配奖励，另一个用零知识（ZK）阈值证明隐藏个体分数，均铸造不可转让的 use-and-burn 代币。
正文 · 原文
Abstract:Federated learning (FL) systems increasingly rely on blockchain based reward mechanisms to incentivize participation while preserving data privacy. We design and empirically evaluate two complementary Solidity smart contracts for FL reward distribution: the first one that allocates rewards proportionally to a publicly disclosed quality score, and a privacy preserving variant that hides individual quality scores behind a zero-knowledge (ZK) proof of a threshold condition. Both contracts mint a non transferable, use-and-burn token maintaining a trustless incentive structure. We evaluate the two designs through MNIST training with adversarial behavior, including Sybil attacks, zero gradient and random noise, across three independent random seeds.
Our results reveal a fundamental tradeoff between cryptographic privacy and incentive fairness. The privacy preserving architecture strictly degrades system robustness, doubling the adversary's average reward capture while introducing severe outcome variance. This vulnerability is driven by a structural self-inclusion bias within cosine-similarity scoring: as the global model converges, legitimate gradient updates naturally diminish, rendering them statistically indistinguishable from bounded noise. Adversaries exploit this dynamic to systematically breach the ZK threshold, triggering a late stage failure cascade that culminates in absolute adversary monopoly over the reward pool and the total exclusion of honest contributors. Alongside a closed-form theorem formalizing this privacy--Sybil resistance tradeoff, we map strict mainnet deployment boundaries via linear gas scaling models, explicitly incorporating the post-Fusaka EIP-7825 per transaction gas cap. Ultimately, while cryptographically secure, static threshold ZK gates fail as incentive layer fairness mechanisms under realistic FL convergence dynamics on standard benchmarks.
| Comments: | 16 pages, 3 figures, 5 tables. Accepted at the 12th Balkan Conference in Informatics (BCI 2026), Best Paper Award |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) |
| MSC classes: | C.2.4, I.2.6, K.4.4 |
| Cite as: | arXiv:2611.16065 [cs.LG] |
| (or arXiv:2611.16065v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16065 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andreas Sendros [view email]
[v1]
Wed, 11 Nov 2026 22:21:23 UTC (35 KB)
来源：arXiv cs.AI · arxiv.org