Descripción del proyecto
Innovadora plataforma de seguridad contra ataques de inteligencia artificial
Los sistemas de inteligencia artificial (IA) encuentran aplicaciones en diversos campos técnicos. Sin embargo, su adopción expone a los primeros usuarios a vulnerabilidades como la corrupción de datos, el robo de modelos y las muestras de adversarios. La falta de capacidades tácticas y estratégicas para defender, identificar y responder a los ataques contra estos sistemas basados en IA constituye una preocupación importante. Los adversarios explotan esta vulnerabilidad, creando una nueva superficie de ataque que se dirige específicamente a los sistemas de aprendizaje automático y aprendizaje profundo, lo cual supone una amenaza sustancial para sectores críticos como el financiero y el sanitario. Para hacer frente a estos retos, el equipo del proyecto AIAS, financiado por las acciones Marie Skłodowska-Curie, pretende investigar la IA antagónica y desarrollar una innovadora plataforma de seguridad para organizaciones. Dicha plataforma empleará métodos de defensa de IA adversaria, mecanismos de engaño y soluciones de IA explicables para capacitar a los equipos de seguridad, fortificando así los sistemas de IA contra posibles ataques.
Objetivo
In recent years, the digital environment and digital transformation of enterprises of all sizes have made AI-based solutions vital to mission-critical. AI-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 AI 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 AI-based systems. Adversaries have created a new attack surface to exploit AI-system vulnerabilities, targeting Machine Learning (ML) and Deep Learning (DL) systems to impair their functionality and performance. Adversarial AI is a new threat that might have serious effects in crucial areas like finance and healthcare, where AI is widely used. AIAS project aims to perform in-depth research on adversarial AI to design and develop an innovative AI-based security platform for the protection of AI systems and AI-based operations of organisations, relying on Adversarial AI defence methods (e.g. adversarial training, adversarial AI attack detection), deception mechanisms (e.g. high-interaction honeypots, digital twins, virtual personas) as well as on explainable AI solutions (XAI) that empower security teams to materialise the concept of “AI for Cybersecurity” (i.e. AI/ML-based tools to enhance the detection performance, defence and respond to attacks) and “Cybersecurity for AI” (i.e. protection of AI systems against adversarial AI attacks).
Ámbito científico
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- engineering and technologycivil engineeringurban engineeringsmart cities
- engineering and technologyelectrical engineering, electronic engineering, information engineeringinformation engineeringtelecommunicationstelecommunications networksmobile network5G
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencescomputer and information sciencescomputer security
Palabras clave
Programa(s)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Régimen de financiación
HORIZON-TMA-MSCA-SE - HORIZON TMA MSCA Staff ExchangesCoordinador
185 33 PIRAEUS
Grecia