A lightweight backdoor defense framework based on image inpainting
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?
Defense during the aggregation phase can use a robust aggregator based on statistical methods that calculates statistical features of model updates, including average and median, and selects one or more participants as reference to detect malicious updates.
“defenders design a robust aggregator based on statistical methods [194], [208]. By calculating the statistical features of model updates, including average and median, one or more participants are selected as the reference to detect the malicious updates [193], [209].”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [193]
For defenders deployed at the client end, the processing capability becomes an inevitable problem.
“While for the defenders that are deployed at the client end, the processing capability becomes an inevitable problem [50], [193].”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [193]
The citation lists haven’t been fetched yet
References 40 · Cited by 6
- Authors
- Wei, Y., Gao, H., Wang, Y., Gao, Y., & Liu, H.
- Affiliations
- Xidian University (CN)
- Corresponding author
- Gao, Haichang
- Venue
- Neurocomputing
- Publisher
- Elsevier BV
- Published
- 2023-06
- Volume
- 537
- Pages
- 22-36
- ISSN
- 0925-2312 (ISSN-L)
- OpenAlex
- W4362471971
- Cited by
- 6
- References
- 40
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 3
- FWCI
- 0.52
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Neurocomputing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Security and Verification in Computing
- Keywords
- backdoor attacks, backdoor defense, image inpainting, backdoor detection, deep neural network security, lightweight defense
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
