2019
DOI: 10.1109/tdsc.2019.2949041
|View full text |Cite
|
Sign up to set email alerts
|

Secure and Utility-Aware Data Collection with Condensed Local Differential Privacy

Abstract: Local Differential Privacy (LDP) is popularly used in practice for privacy-preserving data collection. Although existing LDP protocols offer high data utility for large user populations (100,000 or more users), they perform poorly in scenarios with small user populations (such as those in the cybersecurity domain) and lack perturbation mechanisms that are effective for both ordinal and non-ordinal item sequences while protecting sequence length and content simultaneously. In this paper, we address the small us… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
41
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 65 publications
(41 citation statements)
references
References 40 publications
0
41
0
Order By: Relevance
“…A general rule of thumb [ 27 ] is , where is the domain size of the i th attribute and N is the data size. Some studies in [ 56 , 67 ] have focused on the scenarios with a small number of users and tried to reduce the sample complexity for all privacy regimes.…”
Section: Discussion and Future Directionsmentioning
confidence: 99%
See 2 more Smart Citations
“…A general rule of thumb [ 27 ] is , where is the domain size of the i th attribute and N is the data size. Some studies in [ 56 , 67 ] have focused on the scenarios with a small number of users and tried to reduce the sample complexity for all privacy regimes.…”
Section: Discussion and Future Directionsmentioning
confidence: 99%
“…To address this, Gursoy et al. [ 56 ] introduced condensed local differential privacy (CLDP) that is also a metric-based privacy notation. Let be a distance metric.…”
Section: Theoretical Summarization Of Ldpmentioning
confidence: 99%
See 1 more Smart Citation
“…The edge can better utilize local contexts practically to strike a balance between privacy and usability. Recent studies reveal the synergistic potential of edge, advanced machine learning and privacy-enhancing mechanisms [16,17].…”
Section: Privacy and Sovereigntymentioning
confidence: 99%
“…LDP can be applied to various data collection scenarios, such as frequency estimation, heavy hitters identification, and frequent itemset mining. Companies in different fields, such as Google [15] and Apple [16], have used LDP protocols to collect users' default browser homepages and search engine settings, which can identify harmful or malicious hijacking user settings [17] and find the most frequently used emojis or words.…”
Section: Introductionmentioning
confidence: 99%