MétaCan
Menu
Back to cohort
Record W4417064347 · doi:10.48550/arxiv.2509.08089

Hammer and Anvil: Toward a Theory of Backdoors in Federated Learning

2025· preprint· en· W4417064347 on OpenAlexfundno aff
Lucas Fenaux, Zheng Wang, Nathan Chung, Florian Kerschbaum

Bibliographic record

VenueArXiv.org · 2025
Typepreprint
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaGovernment of OntarioRoyal Bank of Canada
KeywordsBackdoorAdversarySet (abstract data type)InferenceFederated learningAdversarial system

Abstract

fetched live from OpenAlex

Federated Learning (FL) enables distributed model training but is vulnerable to backdoor attacks, where malicious clients embed attacker-controlled behaviors into the global model. Existing defenses fail against adaptive adversaries. In this paper, we present "Hammer and Anvil", a principled theoretical framework that categorizes backdoors by the deviation, $δ$, of their updates to the mean of the updates. We identify two fundamental defense types: "Type 1 (The Anvil)", comprising outlier detection and robust aggregation effective against large-deviation attacks, and "Type 2 (The Hammer)", consisting of removal-based defenses effective against small-deviation attacks. We demonstrate that defenses of a single type and non-principled combined defenses inherently leave an exploitable gap for adaptive attackers. To bridge this gap, we propose the principled combination of Type 1 and Type 2 defenses. We evaluate our framework against a new, worst-case, full-information adaptive adversary that knows the benign updates, the aggregation algorithm, and its parameters, and yet this adversary fails against our combined defenses. Our empirical evaluation across various datasets and settings shows that single-typed and non-principled combined defenses are easily broken, often by a single malicious client. In contrast, our best combined defense variants, $HA_{Flame}^{CSFT}$, $HA_{Krum}^{CSFT}$, and $HA_{Multi-Metrics}^{CSFT}$, remain undefeated even in the most adversarial settings. Our results provide a principled approach for research on backdoors in federated learning.

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)0.021
metaresearch head score (Gemma)0.055
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: Methods · Consensus signal: Methods
Teacher disagreement score0.021
Threshold uncertainty score0.112

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0210.055
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0030.003
Bibliometrics0.0030.003
Science and technology studies0.0030.012
Scholarly communication0.0060.013
Open science0.0060.013
Research integrity0.0050.013
Insufficient payload (model declined to judge)0.0020.001

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 head0.038
GPT teacher head0.287
Teacher spread0.249 · 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
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

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueArXiv.orgSame topicAdversarial Robustness in Machine LearningFrench-language works237,207