Search Results

Facial recognition software (FRS) is a form of biometric security that detects a face, analyzes it, converts it to data, and then matches it with images in a database. This technology is currently being used in vehicles for safety and convenience features, such as detecting driver fatigue, ensuring ride share drivers are wearing a face covering, or unlocking the vehicle. Public transportation hubs can also use FRS to identify missing persons, intercept domestic terrorism, deter theft, and achieve other security initiatives. However, biometric data is sensitive and there are numerous remaining questions about how to implement and regulate FRS in a way that maximizes its safety and security potential while simultaneously ensuring individual’s right to privacy, data security, and technology-based equality.

We describe how we apply the SAE AS 5506 Architecture and Analysis Design Language (AADL) [4] to reason about contextual and architectural concerns for cyber security. A system’s cyber security certification requires verification that the system’s cyber security mechanisms are correct, non-bypassable, and tamper-resistant. We can verify correctness by examining the mechanism itself, but verifying the other qualities requires us to examine the context in which that mechanism resides. Understanding that context and validating the system’s evolving design against that context is an objective for the Architecture Centric Virtual Integration Process (ACVIP), an AADL-based approach to model and detect system design defects before they become too costly to fix. We describe our work to apply AADL to assess non-bypassability and tamper-resistance. The results of our research - tool plugins for cyber security architectural validation - support system developers today in their ACVIP activities.