Malicious Login Detection

If you need to understand how to interact with the Aqora platform first, please follow our tutorial.

Winners will have the opportunity to showcase their work to a global audience and potentially collaborate with NovaceneAI on further developing their solutions.

Suspicious login detection is a cornerstone of cybersecurity efforts, essential for identifying potential breaches and unauthorized access. Current approaches, predominantly rooted in classical machine learning algorithms, face challenges in terms of speed, accuracy, and the management of false positives. With the stakes higher than ever, there is a pressing need for more advanced solutions that can outperform existing methods.

This competition invites participants to explore how quantum computing can revolutionize the field of cybersecurity. Participants will tackle a binary classification problem focused on improving the detection of suspicious logins. By potentially offering superior speed and accuracy, quantum computing holds the promise to significantly reduce false positives and ensure that true threats are not overlooked.

The competition will utilize the BETH dataset, an open-source collection of high-quality cybersecurity data specifically curated for anomaly detection research. This rich dataset provides a realistic foundation for developing and testing innovative approaches to cybersecurity challenges.

Your task is to develop a quantum computing-based model that can more effectively identify suspicious login attempts. We encourage creativity and innovation in employing quantum algorithms to achieve this goal. The solutions will be evaluated based on their accuracy, efficiency, and the ingenuity of the quantum computing techniques applied.