Abstract

As incidents of gendered violence and child abuse increase, there is a need for intelligent, real-time safety systems that autonomously detect distress and initiate emergency action without user activation. Q-SAFE (Quantum AI for Real-Time Women & Child Safety) is an open-source, multi-modal mobile app, utilizing quantum-enhanced machine learning models to detect panic situations based on audio cues (spoken and non-spoken) and motion. The system automatically generates an emergency broadcast that shares live location, messages alerts, and takes videos (in secure cloud storage) in the following ways: automatically detects predetermined distress words using existing Quantum /Indeterminate Natural Language Processing (NLP) classifiers, their corresponding visual module pending; and via accelerometer-based gesture recognition. Most importantly, due to employment of post-quantum cryptographic protocols, the emergency broadcasts use secure communication that does not depend on the users activating any manual processes. Q-SAFE departs from self-activated panic button approaches used in the past noting that fully autonomous systems that require no user activation have been absent for decades. Q-SAFE was developed using scalable technologies, while also conducting tests using multiple scenarios for future robustness, and emerges as an intelligent and privacy-respecting sentinel and caretaker for those that are most vulnerable.

References

Citation

Copy

Copyright

Article metrics