CoChat

A Privacy-Aware and Incremental Defense Method Against GAN-Based Poisoning Attack

Qiao, Feifei, Li, Zhong, Kong, Yubo · 2024 · IEEE Transactions on Computational Social Systems
Cited by 221

The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.

Abstract

Federated learning is usually utilized as a fraud detection framework in the domain of financial risk management, which promotes the model accuracy without training data exchange. One of the challenges in federated learning is the GAN-based poisoning attack. The GAN-based poisoning attack is a type of intractable poisoning attack that causes global model accuracy degradation and privacy leak. Most of the existing defenses for GAN-based poisoning attack have the three problems: 1) dependence on validation datasets; 2) incompetence of dealing with incremental poisoning attack; and 3) privacy leak. To address the above problems, we present a privacy-aware and incremental defense (PID) method to detect malicious participants and protect privacy. In PID, we design a method to accumulate the offset of model parameters from participants in all current epochs to represent the moving tendency for model parameters. Thus, we can distinguish the adversaries from normal participants based on the accumulations in this incremental poisoning attack. We also use multiple trust domains to reduce the rate of misjudging benign participants as adversaries. Moreover, a differentiated differential privacy is utilized before the global model sending to protect the privacy of participants’ training datasets in PID. The experiments conducted on two real-world datasets under financial fraud detection scenario demonstrate that the PID reduces the fallout of adversaries detection (the rate of misjudging benign participants as adversaries) by at least 51.1% and improve the speed of detecting all malicious participants by at least 33.4% compared with two popular defense methods. Besides, the privacy preserving of PID is also effective.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tcss.2023.3263241

Cites

42 of 42 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 5

  1. Blanchard, Machine learning with adversaries: Byzantine tolerant gradient descent, 30, 1
  2. 2022, Credit Card Fraud Detection
  3. 2022, Ccfraud
  4. 10.1016/j.neucom.2020.04.078 · doi:10.1016/j.neucom.2020.04.078
  5. Balle, Improving the Gaussian mechanism for differential privacy: Analytical calibration and optimal denoising, 394

Cited by

See all 221

Metadata

Authors
Qiao, F., Li, Z., & Kong, Y.
Venue
IEEE Transactions on Computational Social Systems
Published
2024-04
Volume
11
Issue
2
Pages
1708-1721
ISSN
  • 2329-924X (ISSN-L)
  • 2373-7476
OpenAlex
W4365790357
Cited by
221
References
42
FWCI
3.07
Type
journal article
Language
en
Open access
closed
Funders
  • National Natural Science Foundation of China (61972080)
  • Natural Science Foundation of Shanghai (23ZR1401000)
  • Shanghai Science and Technology Innovation Action Plan Project (22511100700)
  • Open Foundation of the Key Laboratory of the Ministry of Education for Embedded System and Service Computing, Tongji University (ESSCKF2021-01)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.