Resumen
ln recent years, the digital environment and digital transformation of enterprises of all sizes
have made Al-based solutions vital to mission- critical. Al-based systems are used in every
technical field, including smart cities, self-driving cars, autonomous ships, 5G/6G, and next-
generation intrusion detection systems. The industry's significant exploitation of Al systems
exposes early adopters to undiscovered vulnerabilities such as data corruption, model theft, and
adversarial samples because of their lack of tactical and strategic capabilities to defend,
identify, and respond to attacks on their Al-based systems. Adversaries have created a new attack
surface to exploit Al- system vulnerabilities, targeting Machine Learning (ML) and Deep Learning
(DL) systems to impair their functionality and performance. Adversarial Al is a new threat that
might have serious effects in crucial areas like finance and healthcare, where Al is widely used.
AlAS project aims to perform in-depth research on adversarial Al to design and develop an
innovative Al-based security platform for the protection of Al systems and Al-based operations of
organisations, relying on Adversarial Al defence methods (e.g., adversarial training, adversarial
Al attack detection), deception mechanisms (e.g., high-interaction honeypots, digital twins,
virtual personas) as well as on explainable Al solutions (XAl) that empower security teams to
materialise the concept of "Al for Cybersecurity" (i.e., Al/ML-based e detection performance,
defence and respond to attacks) and "Cybersecurity for Al" (i.e., protection of Al systems
against adversarial Al attacks).
