FlexiNet: Lightweight Traffic Fingerprinting for Resource-Constrained Environments

Network traffic fingerprinting is a valuable method for network monitoring enabling device identification and intrusion detection. Most of the fingerprinting methods utilize machine learning models. Since accuracy is a main concern in networking systems that employ traffic fingerprinting, the underlying models are also tuned to achieve high accuracy. While these systems are mostly deployed in dedicated servers with abundant computational power, in some cases models need to be deployed in resource-constrained environments such as edge servers, and routers. Thus in addition to accuracy, the computational overhead of the system should also be considered while tuning the models. In this paper, we present FlexiNet a lightweight network traffic fingerprinting system for resource-constrained environments. It relies on a genetic algorithm to make multi-objective tuning of hyperparameters of the models to optimize the system based on accuracy, and computational overhead (processing time, CPU, and memory usage). We evaluated FlexiNet in identifying 20 devices in a resource-limited environment with network traffic fingerprinting. We observed that with multi-objective optimization, FlexiNet can reduce processing time and memory usage by 7% and 56% respectively while compromising from f1-score only by 2% and achieving a score of 96%. We also observed that with a lightweight machine learning framework, FlexiNet can reduce time and memory overhead by more than 10% in different platforms.