MétaCan
Menu
Back to cohort
Record W4393032351 · doi:10.1109/tnet.2024.3377655

More Than Enough is Too Much: Adaptive Defenses Against Gradient Leakage in Production Federated Learning

2024· article· en· W4393032351 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueIEEE/ACM Transactions on Networking · 2024
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsComputer scienceLeakage (economics)ComputationInformation leakageGradient descentArtificial intelligenceComputer securityMachine learningAlgorithmArtificial neural network

Abstract

fetched live from OpenAlex

With increasing concerns on privacy leakage from gradients, various attack mechanisms emerged to recover private data from gradients, which challenged the primary advantage of privacy protection in federated learning. However, we cast doubt upon the real impact of these gradient leakage attacks on production federated learning systems. By taking away several impractical assumptions that the literature has made, we find that these attacks pose a limited degree of threat to the privacy of raw data. In this paper, through a comprehensive evaluation of existing gradient leakage attacks in a federated learning system with practical assumptions, we have systematically analyzed their effectiveness under a wide range of configurations. We first 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. 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 leakage 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.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.877
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0050.001
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 head0.049
GPT teacher head0.276
Teacher spread0.227 · 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