Search for: All records

Abstract In recent years, we have seen rapid growth in the use and adoption of Internet of Things (IoT) devices. However, some loT devices are sensitive in nature, and simply knowing what devices a user owns can have security and privacy implications. Researchers have, therefore, looked at fingerprinting loT devices and their activities from encrypted network traffic. In this paper, we analyze the feasibility of fingerprinting IoT devices and evaluate the robustness of such fingerprinting approach across multiple independent datasets — collected under different settings. We show that not only is it possible to effectively fingerprint 188 loT devices (with over 97% accuracy), but also to do so even with multiple instances of the same make-and-model device. We also analyze the extent to which temporal, spatial and data-collection-methodology differences impact fingerprinting accuracy. Our analysis sheds light on features that are more robust against varying conditions. Lastly, we comprehensively analyze the performance of our approach under an open-world setting and propose ways in which an adversary can enhance their odds of inferring additional information about unseen devices (e.g., similar devices manufactured by the same company).

In this study, nine different statistical models are constructed using different combinations of predictors, including models with and without projected predictors. Multiple machine learning (ML) techniques are employed to optimize the ensemble predictions by selecting the top performing ensemble members and determining the weights for each ensemble member. The ML-Optimized Ensemble (ML-OE) forecasts are evaluated against the Simple-Averaging Ensemble (SAE) forecasts. The results show that for the response variables that are predicted with significant skill by individual ensemble members and SAE, such as Atlantic tropical cyclone counts, the performance of SAE is comparable to the best ML-OE results. However, for response variables that are poorly modeled by individual ensemble members, such as Atlantic and Gulf of Mexico major hurricane counts, ML-OE predictions often show higher skill score than individual model forecasts and the SAE predictions. However, neither SAE nor ML-OE was able to improve the forecasts of the response variables when all models show consistent bias. The results also show that increasing the number of ensemble members does not necessarily lead to better ensemble forecasts. The best ensemble forecasts are from the optimally combined subset of models.