Federated Swarm Intelligence for Adversarial Threat Mitigation through Self-Healing Anomaly Consensus Networks
Bibliographic record
Abstract
Mission-critical networks (MCNs) increasingly depend on distributed intelligence for intrusion detection but remain susceptible to adversarial threats and poisoned feedback. As cyber-physical systems scale, ensuring secure and adaptive anomaly detection across heterogeneous, edge-centric environments is vital. Centralized approaches suffer from latency and single points of failure, while conventional federated learning lacks trust and poisoning resilience. These gaps expose MCNs to inference inconsistencies, delayed mitigation, and adversarial manipulation under real-time constraints. This paper presents a federated swarm intelligence framework for secure anomaly detection and adversarial resilience in MCNs. The system integrates a hybrid global-local anomaly detection model, composed of an autoencoder and an isolation forest with a reputation-based belief propagation protocol. Each node performs local inference and shares Indicators of Compromise (IOCs) with trusted peers. Trust scores are dynamically updated using a similarity-weighted belief function, allowing the swarm to isolate poisoned nodes and maintain robust consensus. A self-healing loop filters malicious contributions from global model updates, ensuring continuous adaptation to threat evolution. Experimental results across TON_IoT, CICIDS2017, and UNSW-NB15 datasets demonstrate improved detection accuracy, reduced false positives, and resilience against up to 30% adversarial node participation. This work establishes a scalable defense paradigm for edge-intelligent, real-time MCN environments.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".