Telefonaktiebolaget Lm Ericsson (publ)

Meisam Mohammady

Makan Pourzandi

Lingyu Wang

Yosr Jarraya

Mourad Debbabi

Mengyuan Zhang

Yuan Hong

Suryadipta Majumdar

Han Wang

Shangyu Xie

A method, system and apparatus are disclosed. According to one or more embodiments, a data node is provided. The data node includes processing circuitry configured to: receive an anomaly estimation for a first privatized dataset, the first private dataset being based on a dataset and a first noise profile, apply a second noise profile to the dataset to generate a second privatized dataset, the second noise profile being based at least on the anomaly estimation, and optionally cause transmission of the second privatized dataset for anomaly estimation.

DPOD: differentially private outsourcing of anomaly detection

A method, system and apparatus are disclosed. In one or more embodiments, a differential privacy, DP, node is provided. The DP node includes processing circuitry configured to: receive a query request; receive a first input corresponding to a utility parameter; receive a second input corresponding to a privacy parameter; select a baseline DP mechanism type based at least on a query request type of the query request, the first input and the second input, where the baseline DP mechanism type includes at least a noise parameter; generate a noise distribution based on the baseline DP mechanism type using a first value of the noise parameter; and determine a DP query result based on applying the noise distribution to the query request applied on a data set.

Utility optimized differential privacy system

A node including processing circuitry configured to: generate anonymized data based at least in part on a first cryptographic key and network data, calculate a coordination vector, generate initialized data based at least in part on the anonymized data, a second cryptographic key and the coordination vector, transmit the initialized data, the random vector, a security policy and instructions to analyze n iterations of the initialized data and the security policy using the random vector and the second cryptographic key, and receive results of the analysis of the n iterations of the initialized data and the security policy using the random vector and the second cryptographic key. The analysis of an m iteration of the n iterations correspond to an analysis of the initialized data with prefix preservation where the analysis of the remaining iterations of the n iterations fail to be prefixed preserved.

Partition-based prefix preserving anonymization approach for network traces containing IP addresses

Growing community of inventors

Montreal, Canada

Meisam Mohammady