Social network data is widely shared, transferred and published for research purposes and business interests, but it has raised much concern on users’ privacy. Even though users’ identity information is always removed, attackers can still de-anonymize users with the help of auxiliary information. To protect against de-anonymization attack, various privacy protection techniques for social networ...

Abstract Privacy protection in the computer vision field has attracted increasing attention. Generative adversarial network-based methods have been explored for identity anonymization, but they do not take into consideration semantic information of images, which may result unrealistic or flawed facial results. In this paper, we propose a Semantic-aware De-identification Adversarial Network (SDG...

Anonymization provides a mechanism for sharing data while obscuring private/sensitive values within the shared data. However, anonymization for sharing also sets up a fundamental tradeoff – the stronger the anonymization protection, the less information remains for analysis. This privacy/analysis tradeoff has been descriptively acknowledged by many researchers but no one has yet attempted to qu...

Anonymization is the process of removing or hiding sensitive information in logs. Anonymization allows organizations to share network logs while not exposing sensitive information. However, there is an inherent trade off between the amount of information revealed in the log and the usefulness of the log to the client (the utility of a log). There are many anonymization techniques, and there are...

Following the trend of data trading and data publishing, many online social networks have enabled potentially sensitive data to be exchanged or shared on the web. As a result, users’ privacy could be exposed to malicious third parties since they are extremely vulnerable to de-anonymization attacks, i.e., the attacker links the anonymous nodes in the social network to their real identities with ...

Social Networking Systems (SNSs), such as Facebook, are complex information systems involving a huge number of active entities that provide and consume enormous amounts of information. Such information can be mainly attributed to the users of SNSs and hence, can be considered privacy-sensitive. Therefore, in contrast to traditional systems where access control is governed by system policies, en...

Anonymization of datasets is an important problem in many different scenarios: the census bureau publishes anonymized information, hospitals want to make anonymized patient records available to health researchers, or network service provides might want to publish network traces. Anonymization techniques have have been investigated widely in the past few years [Sweeney, 2002; Machanavajjhala et ...

ISPs are increasingly reluctant to collect and store raw network traces because they can be used to compromise their customers’ privacy. Anonymization techniques mitigate this concern by protecting sensitive information. Trace anonymization can be performed offline (at a later time) or online (at collection time). Offline anonymization suffers from privacy problems because raw traces must be st...

Raw network traces can be used to compromise the privacy of Internet users. For this reason, many ISPs are reluctant to collect network traces – they often regard possession of such traces as a liability. To mitigate this concern, anonymization techniques have been developed to protect user-identifying information. While most projects anonymize their traces as a post-processing step (i.e., offl...