Skip to content
Conference

FedShield: A Dual Algorithm Defense Against Backdoor and Poisoning Attacks in Federated Learning

Aug 2026 · International Conference on Computing Communication Control and automation · pp. 1-8 · 0 citations · 21 references

Abstract

Federated Learning (FL) allows multiple clients to train a single model across devices, safeguarding data privacy in decentralised setups. However, while data does not leave the client, clients can still manipulate the model updates. This makes FL susceptible to poisoning and backdoor attacks. Backdoor attacks are particularly insidious. Today's attacks craft gradients that appear benign, making traditional approaches like filter based on distance to a parameter or gradient norm useless. Existing aggregation methods (Krum, coordinate median, norm filtering) rely on the assumption that malicious updates are easily identified as outlier updates. However, cunning attackers can hide their updates. Relying on a single indicator may not be sufficient. To overcome this, we present FedShield, an additional server-side layer which validates client updates before aggregation. FedShield uses not just one indicator. It uses two complementary checks. BSG tests if a client update produces unusual behavior on a proxy data set. LLGA checks whether gradients of the final layer behave oddly. These are combined to form a trust score, which is then compared to a dynamic threshold to determine which clients are malicious. Anomalies in client behavior and anomalies in gradient structure provide complementary indicators of suspicious activity, making detection considerably harder to evade than with either signal alone. Evaluation with BadNets, label flipping and model replacement attacks demonstrate that FedShield detects all malicious clients without false alarms. It also reduces the attack success and preserves the accuracy of the normal model. Additional tests show that using only BSG or only LLGA is less effective, which suggests both signals are needed.

View source

Similar papers

Open access 2026

SiftFL: Scheduling-Based Robust Backdoor Detection in Federated Learning

SiftFL is proposed, a scheduling-based robust backdoor detection method that sifts out malicious client models at a fraction of the original cost and preserves and improves the robustness of CGAN-based detection while sharply lowering its server-side cost.

Ekhlas Hashem, Muhamad Felemban, Sajjad Mahmood et al. · 0 citations
#federated learning Open access Oct 2026

RFLDefense: robust federated learning defense against targeted attacks

Experimental results on three widely used datasets demonstrate that RFLDefense can effectively defend against various backdoor attacks, outperforming existing defense algorithms while having minimal impact on model utility.

Xiu-Jin Shi, Jia-Wei Gong, Yong-Quan He · 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
#artificial intelligence Preprint Sep 2026

Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning

FedMAST is proposed, a Federated Multi-Axis Structural Tracing defense for backdoor detection in federated learning that uses squeeze-pair coherence scoring to expose coupled feature distortions and signed spectral-drift tracking to reveal persistent directional changes over time.

Srinivasan Subramanian, Md Abdullah Al Hafiz Khan, Kazi Aminul Islam · 0 citations
#federated learning Open access Oct 2026

VDFedDiff: a novel versatile defense scheme against adversarial attacks in federated diffusion models

Federated learning (FL) enables multiple clients to collaboratively train machine learning models without sharing their raw data, making it a promising paradigm for privacy-sensitive generative applications. However, diffusion models trained in federated environments remain vulnerable to backdoor, evasion, and model-po...

Wen-Nan Wang, Tu-Li Chen, Fu Luo · 0 citations
Conference Aug 2026

FedShield: A Privacy-Preserving Federated Learning Framework for Behavioral Detection and Mitigation of Zero-Day Attacks

Zero-day is a type of attack that targets vulnerabilities unknown to vendors and security experts. Traditional signature-based intrusion detection systems fail to flag such attacks. ML models used to detect attacks require data aggregation, which raises substantial privacy concerns and infringes on an organization’s da...

Gargi Chaudhari, Zenia Nouphal, S. Vengurlekar · 0 citations

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