Real-time Netshuffle: Graph distortion for on-line anonymization

Abstract

Due the significant need for real-time anonymization we propose Real-time Netshuffle [1]; a complete graph distortion technique designed to mitigate risk to inference attacks in traffic anonymization. Real-time Netshuffle provides an additional layer of security, in concert with other on-line traffic anonymization techniques, while imposing only minimal damage to the empirical value of the data.

A study of usability-aware network trace anonymization

“…However, a smaller difference might indicate better usability but then low privacy, as anonymized results might be closer to the original data in similarity. Depending on the machine-learning algorithm used, the classification error metric will be in this form [36]: (14) Where Z is the anonymized data, X the original data, and CE is the classification error.…”

“…However, McSherry, Frank, and Mahajan (2011), in their study of applying differential privacy on network trace data, acknowledged the challenges of balancing usability and privacy, despite the confidentiality assurances accorded by differential privacy [13]. On real time interactive anonymization, Paul, Valgenti, and Kim (2011) proposed the Real-time Netshuffle anonymization technique whereby distortion is done to a complete graph to prevent inference attacks in network traffic [14]. Netshuffle works by employing k-anonymity methodology on network traces, by ensuring that all trace records appear at least k>1, with k being the anonymized record, and then shuffling gets applied on the kanonymized records, making it difficult for an attacker to decipher due to the distortion [14].…”

“…On real time interactive anonymization, Paul, Valgenti, and Kim (2011) proposed the Real-time Netshuffle anonymization technique whereby distortion is done to a complete graph to prevent inference attacks in network traffic [14]. Netshuffle works by employing k-anonymity methodology on network traces, by ensuring that all trace records appear at least k>1, with k being the anonymized record, and then shuffling gets applied on the kanonymized records, making it difficult for an attacker to decipher due to the distortion [14]. A network trace obfuscation methodology, (k, j)-obfuscation, was proposed by Riboni, Villani, Vitali, Bettini, and Mancini (2012), in which a network flow is considered obfuscated if it cannot be linked with greater assurance, to its source and destination IP addresses [15].…”

Feature Extraction and Diagnosis of Periodic Transient Impact Faults Based on a Fast Average Kurtogram–GhostNet Method

“…Huang and others [11] introduced a multi-scale convolutional network that enhanced the model's expressive power by adding a multi-scale cascading layer in front of the regular CNN, but this also significantly increased the computational load, making it difficult to deploy the model on resource-limited mobile or embedded devices. To address efficiency and storage issues, lightweight network designs, like MobileNet, ShuffleNet and SqueezeNext, emerged [12][13][14]. Although these models achieve remarkable performance with minimal floating points, they do not fully utilize the correlations and redundancies between feature maps.…”