The automated identification and evaluation of potential attack paths within infrastructures is a critical aspect of cybersecurity risk assessment. However, existing methods become impractical when applied to complex infrastructures. While machine learning (ML) has proven effective in predicting the exploitation of individual vulnerabilities, its potential for full-path prediction remains largely untapped. This challenge stems from two key obstacles: the lack of adequate datasets for training the models and the dimensionality of the learning problem. To address the first issue, we provide a dataset of 1033 detailed environment graphs and associated attack paths, with the objective of supporting the community in advancing ML-based attack path prediction. To tackle the second, we introduce a novel Physics-Informed Graph Neural Network (PIGNN) architecture for attack path prediction. Our experiments demonstrate its effectiveness, achieving an F1 score of $0.9308$ for full-path prediction. We also introduce a self-supervised learning architecture for initial access and impact prediction, achieving F1 scores of $0.9780$ and $0.8214$, respectively. Our results indicate that the PIGNN effectively captures adversarial patterns in high-dimensional spaces, demonstrating promising generalization potential towards fully automated assessments.

Cet article présente une sélection de quatre des treize articles courts du Forum Jeunes Chercheuses Jeunes Chercheurs (JCJC) d’INFORSID 2024. Il offre un panorama de la recherche française menée par des doctorants en systèmes d’information. Ces travaux témoignent de l’engagement de la communauté à développer des systèmes responsables, tant sur le plan sociétal qu’environnemental. Certains explorent également les nouvelles innovations en intelligence artificielle. Cet article aborde divers thèmes tels que la sécurité, l’intégrité de la recherche, l’analyse multimodale de scènes et la frugalité des données.