The pattern of the traffic generated by various applications or the traffic generated by the same application under different circumstances may reveal important insight to the user, the network, the device, or the application. The way a user interacts with the application, the network status and conditions, the server side actions, the device capabilities, degradation or errors during content delivery all influence the protocol and packet level process that can be observed and profiled at the network side through packet sniffing and monitoring. The classification of the profiles enables the identification of typical patterns that can be associated with certain types of user activity, content or application/network behavior. Classification of ongoing application sessions based on their traffic profile enables to detect possible degradations or draw conclusions on the quality perceived by the user. Additionally, such insight when obtained in real time can be used to optimize the content delivery and adapt the treatment of the applications at the network side to better match the user's demand and improve end user quality of experience. Pattern based identification of malicious traffic such as BotNets or spamming is another field where traffic profiling can be applied to improve network security and user privacy. The scope of this work includes: - survey to identify technology enablers and existing methods for traffic profiling - develop mechanisms to detect various traffic patterns under different circumstances - investigate techniques for network side BotNet/spam detection Advantage: - experience in network packet monitoring technologies - well founded mathematical background on statistics

The pattern of the traffic generated by various applications or the traffic generated by the same application under different circumstances may reveal important insight to the user, the network, the device, or the application. The way a user interacts with the application, the network status and conditions, the server side actions, the device capabilities, degradation or errors during content delivery all influence the protocol and packet level process that can be observed and profiled at the network side through packet sniffing and monitoring. The classification of the profiles enables the identification of typical patterns that can be associated with certain types of user activity, content or application/network behavior. Classification of ongoing application sessions based on their traffic profile enables to detect possible degradations or draw conclusions on the quality perceived by the user. Additionally, such insight when obtained in real time can be used to optimize the content delivery and adapt the treatment of the applications at the network side to better match the user's demand and improve end user quality of experience. Pattern based identification of malicious traffic such as BotNets or spamming is another field where traffic profiling can be applied to improve network security and user privacy. The scope of this work includes: - survey to identify technology enablers and existing methods for traffic profiling - develop mechanisms to detect various traffic patterns under different circumstances - investigate techniques for network side BotNet/spam detection Advantage: - experience in network packet monitoring technologies - well founded mathematical background on statistics