Trust-Based Framework for Securing Decentralized Federated Learning against Malicious Clients
Bibliographic record
Abstract
Decentralized federated learning (DFL) enables collaborative model training across distributed clients without relying on a central server. However, this paradigm is highly vulnerable to poisoning attacks, especially when a large proportion of participating clients behave maliciously. In this paper, we propose a robust defense framework that empowers each client to detect and mitigate the influence of malicious peers. Our approach combines local gradient-based anomaly detection using DBSCAN with an uncertainty-aware trust aggregation mechanism grounded in Dempster–Shafer theory. This enables clients to assign trust scores to their neighbors and dynamically perform trust-weighted model aggregation, integrating only reliable updates. Our experiments on two standard benchmark datasets, NSL-KDD and ToN_IoT, show that our method maintains over 93% and 83% accuracy, respectively, even when 70% of clients are adversarial under coordinated label-flipping attacks. These results highlight the robustness and effectiveness of our framework in highly adversarial DFL environments, demonstrating its ability to maintain reliable performance even when the majority of clients behave maliciously.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".