ARTMAN'23 is a workshop co-located with ACM CCS 2023 and sponsored by GRIFIN. It will take place as a post-event workshop on November 30th. Its programme is now published and will feature two keynotes on Secure, intelligent, programmable space-air-ground integrated networks and When Papers Choose Their Reviewers: Adversarial Machine Learning in Peer Review, given by Sandra Scott-Hayward and Konrad Rieck, respectively. It is articulated around 3 technical sessions featuring 5 submissions on Resilience, Robustness and Explainability. The workshop starts at 10:00 and will close at 17:05. See you in Copenhagen!

GRIFIN is financially supporting the ARTMAN'23 workshop, co-located with ACM CCS this year in Copenhagen. ARTMAN is the first workshop on Recent Advances in Resilient and Trustworthy ML Systems in Autonomous Networks. This workshop aims at bringing together academic researchers and industrial practitioners, from different domains with diverse expertise (mainly networking, security, machine learning), to collectively explore and discuss the topics about resilient and trustworthy autonomous networks, share their views, experiences, and lessons learned. It will take place as a post-event workshop on November 30th.

Once again, Solayman will disseminate his progress but, this time, towards a specialized audience as he is attending RESSI 2023, the annual symposium of the French community on the Systems, Software and Networks Security. This annual symposium holds a 3-day program in Neuvy-sur-Barangeon, a rather remote place to encourage interaction, featuring project presentations, research paper replays and training feedback talks. Ph.D students are also invited to present their progress during a poster session, which is preceded by a teasing session where Solayman will have less than 10 minutes to convince people to spend more time discussing in front of the poster. Gregory, our PI, will attend as well to support Solayman in his endeavour.

Solayman, our Ph.D candidate on anomaly detection, has been invited to present the first results of his work at the Annual Symposium of GRIC, the interdisciplinary research group on cybersecurity at the University of Sherbrooke. The symposium took place on April 27th in front of a diverse audience. Solayman did present briefly results on the IDS evaluation framework in more layman’s terms in order to reach out to this broader audience.

A GRIFIN poster on our recent progress will be presented at the French Interdisciplinary Workshop on Global Security (WISG). The workshop is held in the city of Marseille, at the Palais du Pharo from March 21st to 22nd, 2023. On the evening of March 21st, the poster session will be held, where our PI, Gregory, will present the latest results obtained in WP1, in particular the design of our data-driven evaluation framework for ML-based intrusion detection systems.

Solayman’s first paper has been accepted for presentation at the 15th International Symposium on Foundations and Practice of Security (FPS 2022). The paper discusses the proposal of an evaluation framework for ML-based intrusion detection systems. It starts with a survey of recent works in the field of ML-based IDS and provides a comparison of their evaluation methodologies. We notice the lack of rigor with respect to ML best practices when public datasets are used. The corpus of works we studied often fail to anticipate common shortcomings such as unbalance, mislabelling or representativeness of the data. Additionally, although some novel evaluation methodologies were proposed in the field of intrusion detection, the community has been reluctant to apply them broadly. Our proposed framework attempts at combining the advances in both fields to improve the evaluation capabilities of intrusion detection systems that are based on learning models, often sensisitive to the quality of the data. If you happen to be in Ottawa at that time, come and let’s discuss!

Gregory, our PI, presented some first results obtained in Solayman’s thesis with respect to evaluating intrusion detection systems. In particular, the slides presented in Tokyo during the 7th French-Japanese Cybersecurity Workshop dealt with the contributions of AI to the evaluation of IDS, with a focus on dataset generation. GRIFIN’s project results were briefly mentioned with a framework destined to standardize the evaluation of ML-based IDS as proposed by Solayman in his thesis.

Today, it is with heavy heart that the GRIFIN project is relaying the sad news of Thomas Silverston’s passing. He was the coordinator of the LORIA partner, and one of the main supervisors of Solayman’s thesis. It is a huge loss to our project, and also as a friend.

Shurok just joined us at Télécom SudParis, Institut Polytechnique de Paris to work on the second doctoral project on Cognitive and Programmable Response. Before joining us, Shurok was completing an internship at the GRETTIA laboratory, Université Gustave Eiffel. She holds a Master in Intelligent Systems and Applications at Université Gustave Eiffel, where she specialized in modeling, simulation and data analysis of intelligent systems. Her acquired skills in AI and networking will be beneficial to the project.

GRIFIN will be presented at the poster session of the French symposium on the education and research community in information systems security (RESSI, a conference supported by the CNRS research group on cybersecurity (GDR Sécurité Informatique), on May 11th. The poster was teased during a project session. The poster and presentation materials are publicly available (poster) (slides)