I Have a DREAM! (DiffeRentially privatE smArt Metering)
Open accessIntegrity 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?
Shen et al. introduced a statistical mechanism called AUROR to detect malicious users while generating an accurate model.
“Shen et al. [139] introduced a statistical mechanism called AUROR to detect the malicious users while generating an accurate model.”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [139]
The accuracy of a model trained using AUROR drops by only 3% even when 30% of all the users are adversarial.
“The accuracy of a model trained using AUROR drops by only 3% even when 30% of all the users are adversarial.”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [139]
AUROR is based on the observation that indicative features from the majority of honest users will exhibit a similar distribution while those from malicious users will exhibit an anomalous distribution.
“AUROR is based on the observation that indicative features (most important model features) from the majority of honest users will exhibit a similar distribution while those from malicious users will exhibit an anomalous distribution.”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [139]
There is an inherent conflict between privacy and robustness: defending against robustness attacks usually requires complete control of the training process or access to the training data, which goes against the privacy requirements of FL.
“However, it is important to highlight that there is an inherent conflict between privacy and robustness: defending against robustness attacks usually require complete control of the training process or access to the training data [193], [139], [22], [23], [37], [194], which goes against the privacy requirements of FL.”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [139]
The citation lists haven’t been fetched yet
References 22 · Cited by 388
- Authors
- Ács, G., & Castelluccia, C.
- Affiliations
- Institut national de recherche en sciences et technologies du numérique (FR)
- ORCID
- Ács, Gergely
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2011
- Pages
- 118-132
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W1952161176
- Cited by
- 388
- References
- 22
- Citations by year
- 2026: 9 · 2025: 9 · 2024: 21 · 2023: 21 · 2022: 25 · 2021: 36 · 2020: 43 · 2019: 35 · 2018: 31 · 2017: 34 · 2016: 34 · 2015: 33 · 2014: 25 · 2013: 22 · 2012: 8
- FWCI
- 14.27
- Type
- conference paper
- Language
- en
- Open access
- green
- zenodo.org
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Engineering › Control and Systems Engineering › Smart Grid Security and Resilience
- Physical Sciences › Computer Science › Artificial Intelligence › Internet Traffic Analysis and Secure E-voting
- Keywords
- differential privacy, smart metering, privacy-preserving data collection, electricity consumption data
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
