A uror: defending against poisoning attacks in collaborative deep learning systems
Abstract
Deep learning in a collaborative setting is emerging as a corner-stone of many upcoming applications, wherein untrusted users collaborate to generate more accurate models. From the security perspective, this opens collaborative deep learning to poisoning attacks, wherein adversarial users deliberately alter their inputs to mis-train the model. These attacks are known for machine learning systems in general, but their impact on new deep learning systems is not well-established.
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?
Mirai is a highly relevant baseline for IoT malware behavior because its source code is publicly available, variants use the same code base, and it realizes similar attack stages as state-of-the-art IoT malware.
“We selected Mirai for this purpose, since its source code is publicly available and several infamous malware variants like Hajime [2] or Persirai [27] have been implemented using the same code base.Mirai also realizes similar attack stages (detailed in Sect.V-A3 below) as stateof-the-art IoT malware [3], [28].This makes Mirai a highly relevant baseline for IoT malware behavior.”
From DÏoT: A Federated Self-learning Anomaly Detection System for IoT (2019) · cites this paper as [2]
DÏOT is likely effective also in detecting other botnet malware like Persirai and Hajime.
“D ÏOT is likely effective also in detecting other botnet malware like Persirai [27], Hajime [2], etc.”
From DÏoT: A Federated Self-learning Anomaly Detection System for IoT (2019) · cites this paper as [2]
FL workflow can be realized with diverse topologies; the two most common are the centralized approach via an aggregation server or peer-to-peer decentralized approaches.
“FL workflow can be realized with diverse topologies.The two most common ones are either the centralized approach via an aggregation server or peer-to-peer decentralized approaches [126]- [130].”
From Vulnerabilities in federated learning (2021) · cites this paper as [127]
The citation lists haven’t been fetched yet
References 41 · Cited by 228
- Authors
- Shen, S., Tople, S., & Saxena, P.
- Affiliations
- National University of Singapore (SG)
- Venue
- Proceedings of the 32nd Annual Conference on Computer Security Applications
- Publisher
- ACM
- Published
- 2016-12-05
- Pages
- 508-519
- ISSN
- 1063-9527 (ISSN-L)
- OpenAlex
- W2559840118
- Cited by
- 228
- References
- 41
- Citations by year
- 2026: 16 · 2025: 28 · 2024: 39 · 2023: 26 · 2022: 30 · 2021: 24 · 2020: 31 · 2019: 16 · 2018: 12 · 2017: 6
- FWCI
- 6.11
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Annual Computer Security Applications Conference (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Security and Verification in Computing
- Keywords
- collaborative deep learning, poisoning attacks, adversarial examples, untrusted users, data poisoning
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
