MétaCan
Menu
Back to cohort
Record W4220733056 · doi:10.18280/ria.360106

Security of Federated Learning: Attacks, Defensive Mechanisms, and Challenges

2022· article· en· W4220733056 on OpenAlexvenueno aff
Mourad Benmalek, Mohamed Ali Benrekia, Yacine Challal

Bibliographic record

VenueRevue d intelligence artificielle · 2022
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsnot available
Fundersnot available
KeywordsComputer scienceFederated learningComputer securityTracingTrainPrivate information retrievalData scienceInternet privacyArtificial intelligence

Abstract

fetched live from OpenAlex

Recently, a new Artificial Intelligence (AI) paradigm, known as Federated Learning (FL), has been introduced. It is a decentralized approach to apply Machine Learning (ML) on-device without risking the disclosure and tracing of sensitive and private information. Instead of training the global model on a centralized server (by aggregating the clients’ private data), FL trains a global shared model by only aggregating clients’ locally-computed updates (the clients’ private data remains distributed across the clients’ devices). However, as secure as the FL seems, it by itself does not give the levels of privacy and security required by today’s distributed systems. This paper seeks to provide a holistic view of FL’s security concerns. We outline the most important attacks and vulnerabilities that are highly relevant to FL systems. Then, we present the recent proposed defensive mechanisms. Finally, we highlight the outstanding challenges, and we discuss the possible future research directions.

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 imitation

Not 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.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.030
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.019
Threshold uncertainty score0.101

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.030
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0020.002
Science and technology studies0.0030.007
Scholarly communication0.0090.017
Open science0.0040.008
Research integrity0.0060.008
Insufficient payload (model declined to judge)0.0010.001

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 head0.066
GPT teacher head0.277
Teacher spread0.210 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreReview

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

Citations37
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueRevue d intelligence artificielleSame topicPrivacy-Preserving Technologies in DataFrench-language works237,207