CONTRA: Defending Against Poisoning Attacks in Federated Learning
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The success of data-based backdoor attacks depends on the sufficient number of attack rounds to avoid the dilution of the backdoor effect.
“However, because these attacks only target the training data, their success depends on the sufficient number of attack rounds to avoid the dilution of the backdoor effect [236].”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [236]
The citation lists haven’t been fetched yet
References 34 · Cited by 182
- Authors
- Awan, S., Luo, B., & Li, F.
- Affiliations
- University of Kansas (US)
- Corresponding author
- Li, Fengjun
- ORCID
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2021
- Pages
- 455-475
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W3203600060
- Cited by
- 182
- References
- 34
- Citations by year
- 2026: 24 · 2025: 51 · 2024: 54 · 2023: 38 · 2022: 14 · 2021: 1
- FWCI
- 12.36
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- federated learning, poisoning attacks, attack defense, label-flipping attacks, backdoor attacks, cosine similarity, non-IID data, malicious clients
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
