Projects

The utilization of Deep Learning (DL) models in identifying security threats has proven to be highly successful. However, these models have shown limitations in generalizing to real-world scenarios due to their data-driven nature, leading to learned patterns that are often biased.

RE-AIS refers to humans’ semantic knowledge of domain concepts to establish a benchmark for assessing the quality of AIS randomly-collected training datasets. Within this framework, a process is implemented to extract common social specifications of primary concepts in a domain, which in turn, derives useful knowledge to be passed to AIS, such that domain specifications are well-met within the intelligent model.