Passive cyber-security attacks do not require any modification of the data stream generated by the victim. They are based on statistical analysis of traffic patterns.
The Physical Downlink Control Channel, transmitted in clear text, may be effectively used to statistically characterize the traffic generated by a smartphone in standby mode. Through this statistical signature, the attacker may then infer whether an unknown traffic pattern is generated by the victim user's terminal.
Obtaining such signatures is the goal of this project. To do so, user data patterns are retrieved from the mobile network scheduling. After that, a sequence-to-sequence learning framework is proposed to extract smartphone signatures from the collected traffic data.