MétaCan
Menu
Back to cohort

More than Enough is Too Much: Adaptive Defenses against Gradient Leakage in Production Federated Learning

2023· article· en· W4386245223 on OpenAlexaff
Wang Fei, Ethan Hugh, Baochun Li

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsComputer scienceLeakage (economics)ComputationGradient descentInformation leakageArtificial intelligenceComputer securityAlgorithmMachine learningArtificial neural network

Abstract

fetched live from OpenAlex

With increasing concerns on privacy leakage from gradients, a variety of attack mechanisms emerged to recover private data from gradients at an honest-but-curious server, which challenged the primary advantage of privacy protection in federated learning. However, we cast doubt upon the real impact of these gradient attacks on production federated learning systems. By taking away several impractical assumptions that the literature has made, we find that gradient attacks pose a limited degree of threat to the privacy of raw data.Through a comprehensive evaluation on existing gradient attacks in a federated learning system with practical assumptions, we have systematically analyzed their effectiveness under a wide range of configurations. We present key priors required to make the attack possible or stronger, such as a narrow distribution of initial model weights, as well as inversion at early stages of training. We then propose a new lightweight defense mechanism that provides sufficient and self-adaptive protection against time-varying levels of the privacy leakage risk throughout the federated learning process. As a variation of gradient perturbation method, our proposed defense, called Outpost, selectively adds Gaussian noise to gradients at each update iteration according to the Fisher information matrix, where the level of noise is determined by the privacy leakage risk quantified by the spread of model weights at each layer. To limit the computation overhead and training performance degradation, Outpost only performs perturbation with iteration-based decay. Our experimental results demonstrate that Outpost can achieve a much better tradeoff than the state-of-the-art with respect to convergence performance, computational overhead, and protection against gradient attacks.

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)0.008
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Open science
Consensus categoriesOpen science
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.829
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.008
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0070.026
Research integrity0.0000.000
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 head0.053
GPT teacher head0.276
Teacher spread0.224 · 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; both teacher heads agree on what is shown here.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations24
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicPrivacy-Preserving Technologies in DataFrench-language works237,207