Skip to content
Review Open access

Privacy and Security in Knowledge Distillation for Federated Learning: A Survey

2026 · IEEE Access · Vol 14, pp. 136581-136605 · 0 citations · 61 references

TL;DR

This survey examines KD-based FL through a privacy and security lens, and provides a precise framework for evaluating what KD-FL methods actually guarantee and what they only make harder for an adversary.

Abstract

Knowledge distillation (KD) is increasingly used in federated learning (FL) because it enables clients to exchange predictions, features, prototypes, or synthetic knowledge rather than full model parameters. This change can reduce communication and support heterogeneous models, but it also changes the privacy and security threat surface rather than eliminating it. This survey examines KD-based FL through a privacy and security lens. We distinguish formal differential-privacy guarantees, protocol-level cryptographic mechanisms, structural reductions of the attack surface, and empirical attack-specific defenses, and we map these notions to transfer direction, shared representation, and data-availability assumptions. We review attacks against released distilled knowledge, privacy-preserving distillation mechanisms, secure aggregation and encrypted-domain approaches, adversarial defenses, application domains, and open challenges for formal assurance and standardized benchmarking. The goal is to provide a precise framework for evaluating what KD-FL methods actually guarantee and what they only make harder for an adversary.

Read PDF

Similar papers

Review Open access Sep 2026

Bridging ML and Threat Landscapes: Inference Attacks and Cryptographic Defenses for Training-Phase Data Protection

Machine learning systems use sensitive personal data to train and infer models, but developers are largely unaware of privacy attack vectors that evade conventional data security controls. This paper surveys the privacy threat landscape inherent to ML workflows, including membership inference attacks, model inversion a...

Pramod Prakash · 0 citations
Open access Aug 2026

SecureFedShield: An Adaptive Privacy-Preserving Federated Defense Framework Against Adversarial Attacks in Financial Fraud Detection

SecureFedShield is proposed, a privacy-preserving federated learning framework designed for secure financial fraud detection in adversarial environments that integrates adaptive privacy protection, trust-aware client evaluation, adversarial update detection, and robust model aggregation into a unified architecture.

Kriti Mishra · 0 citations

PNFR: practicality-enhanced and non-interactive privacy-preserving federated regressions

PNFR is designed, a privacy-preserving federated learning scheme for regressions training built on the MPaillier algorithm, which is three times faster than interactive federated regressions PrivFL and about 80% faster than non-interactive federated regressions VANE.

Hui-Yu Xie, Tan-Ping Zhou, Shuo Chen et al. · 0 citations
Preprint Aug 2026

BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

BackDFL is presented, a unified benchmark for systematically evaluating DFL under realistic and adaptive backdoor attacks, and demonstrates that both state-of-the-art Byzantine-robust DFL methods and adapted FL backdoor defenses fail under modest malicious participation rates, especially in heterogeneous settings.

M. Bouchiha, Gregory Blanc, Yu-Fei Han · 0 citations
Review Sep 2026

Privacy-preserving methodologies against privacy attacks on deep learning: a survey

The analysis finds that noise-based methods such as DP remain the practical baseline but offer only partial protection; cryptographic approaches provide stronger theoretical guarantees at substantially higher cost; and LLM/multimodal leakage remains an urgent, under-benchmarked gap.

Subhasish Ghosh, A. K. Mandal · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.