Right-Protected Data Publishing with Provable Distance-Based Mining

Zoumpoulis, Spyros I.; Vlachos, Michail; Freris, Nikolaos M.; Lucchese, Claudio

doi:10.1109/tkde.2013.90

Cited by 8 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of watermarking in data-mining and databases, prior work examined how to right-protect data tables [11], data streams [12] and numeric datasets [16,15]. The latter works are the most relevant to the present work on right protection, because they also attempt to mitigate the effect of watermarking on the utility of the resulting dataset.…”

Section: Related Workmentioning

confidence: 99%

Private and Right-Protected Big Data Publication: An Analysis

Heckel

Vlachos²

2017

Proceedings of the 2017 SIAM International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

The ease of digital data dissemination has spurred an amplified interest in technologies related to data privacy and right protection. We examine how both goals can be achieved simultaneously by constructing modified data instances that are both differentially private and right protected. The proposed method first produces a sketch of the dataset via random projection and then perturbs the sketch just enough to ensure privacy. The right-protection mechanism inserts small noise in the dataset which subsequently can be used to verify ownership. We provide analytical privacy, right-protection, and utility guarantees. Our utility guarantees ensure approximate preservation of pairwise distances, thus mining operations such as search, classification, and clustering can be performed on the differentially private and right protected dataset.Extended version with proofs:

show abstract

Section: Related Workmentioning

confidence: 99%

Private and Right-Protected Big Data Publication: An Analysis

Heckel

Vlachos²

2017

Proceedings of the 2017 SIAM International Conference on Data Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…This work is different from just traditional watermarking which focused on privacy preservation, as scheme [3][6] not only works on perturbed data but also distance preservation by using NN and MST so that it can be relevantly used where distance relationship preservation is important property like in various data mining and machine learning algorithms.…”

Section: Litreture Surveymentioning

confidence: 99%

“…Because of constraints provided by the lower and upper bound the two objects that are at some specific distance with each other cannot get far apart or too close after watermark embedding [3]. This is done by establishing restricted isometric property which makes watermark embedding power to lie in the interval [ρ min , ρ max ] ⊆ 0,1…”

Section: Lower and Upper Bounds On Distance Distortionmentioning

confidence: 99%

See 2 more Smart Citations

Watermarking Shape Datasets with Utility and Distance Preservation

Gupta¹,

Patil²,

Chandode³

2016

IJCA

View full text Add to dashboard Cite

Due to promulgation of data over internet significance of protection of one's intellectual property is the important topic with technological and legal aspects. Watermarking scheme is used for establishing the ownership of dataset containing multiple objects. As watermarking scheme distorts distance relationship graph, methodology preserves utility of dataset by preserving important distance properties such as nearest neighbor (NN) and minimum spanning tree (MST) of the original data set. We use fast algorithms for NN and MST which gives improved security without any sacrifice in distance relationships then NN and MST algorithms used earlier. KeywordsAlgorithm, fast nearest neighbor algorithm, minimum spanning tree algorithm, fast minimum spanning tree algorithm

show abstract

A software-defined architecture for control of IoT cyberphysical systems

Darabseh¹,

Freris

2019

Cluster Comput

Self Cite

View full text Add to dashboard Cite

Based on software-defined principles, we propose a holistic architecture for Cyberphysical Systems (CPS) and Internet of Things (IoT) applications, and highlight the merits pertaining to scalability, flexibility, robustness, interoperability, and cyber security. Our design especially capitalizes on the computational units possessed by smart agents, which may be utilized for decentralized control and in-network data processing. We characterize the data flow, communication flow, and control flow that assimilate a set of components such as sensors, actuators, controllers, and coordinators in a systemic programmable fashion. We specifically aim for distributed and decentralized decision-making by spreading the control over several hierarchical layers. In addition, we propose a middleware layer to encapsulate units and services for time-critical operations in highly dynamic environments. We further enlist a multitude of vulnerabilities to cyberattacks, and integrate softwaredefined solutions for enabling resilience, detection and recovery. In this purview, several controllers cooperate to identify and respond to security threats and abnormal situations in a self-adjusting manner. Last, we illustrate numerical simulations in support of the virtues of a software-defined design for CPS and IoT.

show abstract

Right-Protected Data Publishing with Provable Distance-Based Mining

Cited by 8 publications

References 19 publications

Private and Right-Protected Big Data Publication: An Analysis

Private and Right-Protected Big Data Publication: An Analysis

Watermarking Shape Datasets with Utility and Distance Preservation

A software-defined architecture for control of IoT cyberphysical systems

Contact Info

Product

Resources

About