Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Client-Verifiable and Efficient Federated Unlearning in Low-Altitude Wireless Networks

Yuhua Xu, Mingtao Jiang, Chenfei Hu, Yinglong Wang, Chuan Zhang, Meng Li, Ming Lu, Liehuang Zhu

Abstract

In low-altitude wireless networks (LAWN), federated learning (FL) enables collaborative intelligence among unmanned aerial vehicles (UAVs) and integrated sensing and communication (ISAC) devices while keeping raw sensing data local. Due to the "right to be forgotten" requirements and the high mobility of ISAC devices that frequently enter or leave the coverage region of UAV-assisted servers, the influence of departing devices must be removed from trained models. This necessity motivates the adoption of federated unlearning (FUL) to eliminate historical device contributions from the global model in LAWN. However, existing FUL approaches implicitly assume that the UAV-assisted server executes unlearning operations honestly. Without client-verifiable guarantees, an untrusted server may retain residual device information, leading to potential privacy leakage and undermining trust. To address this issue, we propose VerFU, a privacy-preserving and client-verifiable federated unlearning framework designed for LAWN. It empowers ISAC devices to validate the server-side unlearning operations without relying on original data samples. By integrating linear homomorphic hash (LHH) with commitment schemes, VerFU constructs tamper-proof records of historical updates. ISAC devices ensure the integrity of unlearning results by verifying decommitment parameters and utilizing the linear composability of LHH to check whether the global model accurately removes their historical contributions. Furthermore, VerFU is capable of efficiently processing parallel unlearning requests and verification from multiple ISAC devices. Experimental results demonstrate that our framework efficiently preserves model utility post-unlearning while maintaining low communication and verification overhead.

Client-Verifiable and Efficient Federated Unlearning in Low-Altitude Wireless Networks

Abstract

In low-altitude wireless networks (LAWN), federated learning (FL) enables collaborative intelligence among unmanned aerial vehicles (UAVs) and integrated sensing and communication (ISAC) devices while keeping raw sensing data local. Due to the "right to be forgotten" requirements and the high mobility of ISAC devices that frequently enter or leave the coverage region of UAV-assisted servers, the influence of departing devices must be removed from trained models. This necessity motivates the adoption of federated unlearning (FUL) to eliminate historical device contributions from the global model in LAWN. However, existing FUL approaches implicitly assume that the UAV-assisted server executes unlearning operations honestly. Without client-verifiable guarantees, an untrusted server may retain residual device information, leading to potential privacy leakage and undermining trust. To address this issue, we propose VerFU, a privacy-preserving and client-verifiable federated unlearning framework designed for LAWN. It empowers ISAC devices to validate the server-side unlearning operations without relying on original data samples. By integrating linear homomorphic hash (LHH) with commitment schemes, VerFU constructs tamper-proof records of historical updates. ISAC devices ensure the integrity of unlearning results by verifying decommitment parameters and utilizing the linear composability of LHH to check whether the global model accurately removes their historical contributions. Furthermore, VerFU is capable of efficiently processing parallel unlearning requests and verification from multiple ISAC devices. Experimental results demonstrate that our framework efficiently preserves model utility post-unlearning while maintaining low communication and verification overhead.

Paper Structure

This paper contains 43 sections, 2 theorems, 25 equations, 5 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Federated Unlearning
  4. Cryptographic Primitives
  5. Homomorphic Encryption
  6. Linear Homomorphic Hash
  7. Commitment
  8. The Architecture of Design
  9. Architecture Overview
  10. Local training and Uploading
  11. Encrypted aggregation and unlearning
  12. Broadcasting global model and verifying
  13. Threat Model
  14. Design Goals
  15. Privacy of gradients
  16. ...and 28 more sections

Key Result

Theorem 1

Under the assumptions of the hardness of the discrete logarithm problem and the security of the commitment scheme, VerFU achieves unlearning integrity as formally defined in Definition def4.

Figures (5)

  • Figure 1: The architecture of VerFU.
  • Figure 2: The complete workflow of VerFU.
  • Figure 3: Accuracy performance under dynamic ISAC device unlearning in VerFU.
  • Figure 4: Loss comparison under dynamic ISAC device unlearning in VerFU.
  • Figure 5: Impact of dynamic ISAC device unlearning on model utility in VerFU.

Theorems & Definitions (8)

  • Definition 1: Collision Resistance of Linear Homomorphic Hash
  • Definition 2: Binding of Commitment Scheme
  • Definition 3: Equivocality of Commitment Scheme
  • Definition 4: Integrity of Unlearning
  • Theorem 1
  • Proof 1
  • Theorem 2
  • Proof 2