In this paper we use Facenet, an open-source machine learning cloud platform to verify biometric facial templates created with the ones already enrolled. Our efforts seek to determine if, for different sample images of different ages when evaluated against our pattern matching algorithm, the template policy changes with the aged images. Whilst our approach may hold true for small data set changes that the template policy does not see any anomalies, all other things being equal, as in the results in the current paper, we argue that the template policy could change if we explore the concerns over a large continuous data set as our next step and treated as independent work to this current paper.

This paper presents the case proposal for a cyber-aware cloud operated chatbot service. The paper has in terms of its contributions (i) a design and (ii) a possible framework that detects as well as help to prevent the malware behavior from spreading on the user’s machine. The perspective encapsulates the human understanding of what this malware behavior exhibits, and how the chatbot aids the human user within that context. The Chatbot malicious behavior is modeled based on the vulnerabilities observed within the Open Web Application Security Project (OWASP) top ten [1] which outlines the security vulnerabilities of the web. This work becomes important in the context of chatbots becoming mainstream since the pandemic and the plethora of uses particularly in mission critical enterprises.