Bala Srinivasan

Md Mohaimenuzzaman, Zahraa Said Abdallah, Joarder Kamruzzaman et al.

This paper studies the effect of various hyper-parameters and their selection for the best performance of the deep learning model proposed in [1] for distributed attack detection in the Internet of Things (IoT). The findings show that there are three hyper-parameters that have more influence on the best performance achieved by the model. As a consequence, this study shows that the model's accuracy as reported in the paper is not achievable, based on the best selections of parameters, which is also supported by another recent publication [2].

Orhio Mark Creado, Bala Srinivasan, Phu Dung Le et al.

Trust is an absolute necessity for digital communications; but is often viewed as an implicit singular entity. The use of the internet as the primary vehicle for information exchange has made accountability and verifiability of system code almost obsolete. This paper proposes a novel approach towards enforcing system security by requiring the explicit definition of trust for all operating code. By identifying the various classes and levels of trust required within a computing system; trust is defined as a combination of individual characteristics. Trust is then represented as a calculable metric obtained through the collective enforcement of each of these characteristics to varying degrees. System Security is achieved by facilitating trust to be a constantly evolving aspect for each operating code segment capable of getting stronger or weaker over time.