Unknown Computerized-Attack Recognition via Open-Set Circumstance-Adaptive Learning Approach

Abstract

Cyber threats come in all forms and constantly evolve into newly unknown malicious attacks. The status quo is that current mobile and/or embedded devices are unaware of embedded data with newly unknown threats, making it difficult to predict new threat types. To access much higher mobile security, we have deployed open-set domain adaptation to understand existing information yet still be realizable and recognizable to the novel unseen class instances. Our demonstrations are validated against visual benchmarks, such as handwritten data, and applied to our datasets to verify the embedding of unfamiliar data on embedded devices. As a result, it can gather a lot of information for both known and unknown instances from both datasets. Besides, it raises the issue of what cyber threat data to use in the circumstance like embedding over system-level firmware updates.