MétaCan
Menu
Back to cohort

Securing Multi-Layer Federated Learning: Detecting and Mitigating Adversarial Attacks

2024· article· en· W4402811446 on OpenAlexaff
Justin M. Gouge, Ping Wang

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsYork University
Fundersnot available
KeywordsAdversarial systemComputer scienceLayer (electronics)Computer securityComputer networkArtificial intelligenceNanotechnology

Abstract

fetched live from OpenAlex

Adversarial entities can poison models, slowing down or destroying the training process of federated learning (FL). Therefore, attack prevention and mitigation are crucial for FL. While existing works primarily address attack mitigation in conventional two-layer FL systems, research on attack prevention and mitigation in multi-layer federated learning systems remains limited. In this work, we propose new methods for anomaly detection and removal of attackers from training in a multi-layer FL system. First, we deploy a variational autoencoder (VAE) to detect which edge servers at the cohort level contain malicious clients. Subsequently, we devise two malicious client exclusion strategies: scoring-based and Bayesian-based, aimed at mitigating potential harm caused by these clients during model training. The experimental results demonstrate the superiority of our proposed methods over the previous work under a variety of scenarios.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.803
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0000.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.023
GPT teacher head0.292
Teacher spread0.269 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicAdversarial Robustness in Machine LearningFrench-language works237,207