Machine Learning meets Security
Intelligent Predictive Security by Dragan Pleskonjic
The team, led by INPRESEC initiator Dragan Pleskonjic ( https://www.linkedin.com/in/draganpleskonjic/ ), developed a solution that predicts, prevents and detects security threats and attacks before they actually affect the live system, with demonstrable accuracy of approximately 99%.
The solution utilizes Artificial Intelligence (AI), Machine Learning (ML), predictive analytics, and threat intelligence with a specific approach developed by the team with decades of combined experience in scientific research, academia and professional experience in enterprise security, AI and ML (patent applications in progress).
The solution improves security posture of the client system by minimizing risks and impacts of security threats and attacks. It significantly reduces the work of security teams, while improving accuracy, response time and performances of the security system.
IoT dinosaurs - don’t die out by A. Dulaunoy, G. Wagener
The topic Internet of things (IoT) gains popularity on conferences either about their usefulness or their related security issues. IoT devices are meant to provide data about various sensors but also provide indirect data about the behavior of their operators especially focusing on their management of security vulnerabilities.
The presented behaviors were derived from network blackholes and honeypots. An overview of network devices that are probed, exploited and abused for the last 5 years is presented. Short and long examples are shown. Once a vulnerable device is connected to the Internet it usually takes a long time to get it fixed or removed which provides good denial of service business opportunities.