Threats to adversarial training for IDSs and mitigation
Notre doctorant Hassan Chaitou (Télécom Paris, Sujet P7 : AI based security risk management) participera au 19e « International Conference on Security and Cryptography » (SECRYPT 2022) qui se tiendra du 11 au 13 juillet 2022 à Lisbonne (Portugal). Vous trouverez plus d’informations sur la conférence ici : https://secrypt.scitevents.org/
Cet événement a pour but de solliciter des soumissions de la part du monde universitaire, de l’industrie et du gouvernement présentant des recherches novatrices sur tous les aspects théoriques et pratiques de la protection des données, de la confidentialité, de la sécurité et de la cryptographie.
C’est dans ce cadre qu’Hassan présentera sa communication :
- Full paper Hassan Chaitou, Thomas Robert, Jean Leneutre, & Laurent Pautet, “Threats to adversarial training for IDSs and mitigation“
Voici l’abstract :
Intrusion Detection Systems (IDS) are essential tools to protect network security from malicious traffic. IDS have recently made significant advancements in their detection capabilities through deep learning algorithms compared to conventional approaches. However, these algorithms are susceptible to new types of adversarial evasion attacks. Deep learning-based IDS, in particular, are vulnerable to adversarial attacks based on Generative Adversarial Networks (GAN). First, this paper identifies the main threats to the robustness of IDS against adversarial sample attacks that aim at evading IDS detection by focusing on potential weaknesses in the structure and content of the dataset rather than on its representativeness. In addition, we propose an approach to improve the performance of adversarial training by driving it to focus on the best evasion candidates samples in the dataset. We find that GAN adversarial attack evasion capabilities are significantly reduced when our method is used to strengthen the IDS.
- Les AFTERS by Pôle Excellence Cyber - April 7, 2023
- Federated Learning as enabler for Collaborative Security between not Fully-Trusting Distributed Parties - February 10, 2023
- [RU2/22] Anthony DAVID : Virtual Reality for cybersecurity data vizualisation - December 21, 2022
