MétaCan
Menu
Back to cohort
Record W4319863836 · doi:10.1016/j.dcan.2023.01.017

XMAM:X-raying models with a matrix to reveal backdoor attacks for federated learning

2023· article· en· W4319863836 on OpenAlexaff
Jianyi Zhang, Fangjiao Zhang, Qichao Jin, Zhiqiang Wang, Xiaodong Lin, Xiali Hei

Bibliographic record

VenueDigital Communications and Networks · 2023
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Guelph
FundersFundamental Research Funds for the Central UniversitiesNational University's Basic Research Foundation of China
KeywordsBackdoorComputer scienceSoftmax functionComputer securityArtificial intelligenceComputer networkDeep learning

Abstract

fetched live from OpenAlex

Federated Learning (FL), a burgeoning technology, has received increasing attention due to its privacy protection capability. However, the base algorithm FedAvg is vulnerable when it suffers from so-called backdoor attacks. Former researchers proposed several robust aggregation methods. Unfortunately, due to the hidden characteristic of backdoor attacks, many of these aggregation methods are unable to defend against backdoor attacks. What's more, the attackers recently have proposed some hiding methods that further improve backdoor attacks' stealthiness, making all the existing robust aggregation methods fail. To tackle the threat of backdoor attacks, we propose a new aggregation method, X-raying Models with A Matrix (XMAM), to reveal the malicious local model updates submitted by the backdoor attackers. Since we observe that the output of the Softmax layer exhibits distinguishable patterns between malicious and benign updates, unlike the existing aggregation algorithms, we focus on the Softmax layer's output in which the backdoor attackers are difficult to hide their malicious behavior. Specifically, like medical X-ray examinations, we investigate the collected local model updates by using a matrix as an input to get their Softmax layer's outputs. Then, we preclude updates whose outputs are abnormal by clustering. Without any training dataset in the server, the extensive evaluations show that our XMAM can effectively distinguish malicious local model updates from benign ones. For instance, when other methods fail to defend against the backdoor attacks at no more than 20% malicious clients, our method can tolerate 45% malicious clients in the black-box mode and about 30% in Projected Gradient Descent (PGD) mode. Besides, under adaptive attacks, the results demonstrate that XMAM can still complete the global model training task even when there are 40% malicious clients. Finally, we analyze our method's screening complexity and compare the real screening time with other methods. The results show that XMAM is about 10–10000 times faster than the existing methods.

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)0.003
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.003
Threshold uncertainty score0.017

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.010
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.003
Open science0.0020.004
Research integrity0.0010.003
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 head0.057
GPT teacher head0.311
Teacher spread0.254 · 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 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

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueDigital Communications and NetworksSame topicPrivacy-Preserving Technologies in DataFrench-language works237,207