S2RAI
Safe, Secure and Robust AI Track at the SAC25 Conference
2024/10/04: Very final extension has been granted, up to October, 13th!
2024/09/15: ACM-SAC 2025 (and thus S2RAI) extended the submission deadline to October 4th!
2024/08/26: Updated TPC and first CfP, available HERE!
2024/08/01: TPC List was added to the website (to be integrated later in the month)
2024/06/05: Track website is OUT!
Machine Learning (ML) became the enabling technology of several applications. There is an enormous interest in adopting them to support critical tasks such as error/intrusion/anomaly detection, image classification or even object detection and trajectory planning to support autonomous driving. However, components that operate in critical systems must be assessed so that the encompassing system complies with adequate safety and security requirements before they are deployed and used in their operational environment without generating catastrophic hazards to the health of citizens, the environment, or the infrastructures. The absence of safety/security guarantees, or even a quantitative estimation of their robustness against specific events (e.g., unknown or zero-day attacks, adversarial attacks, out-of-distribution data) may be considered unacceptable by certification bodies, holding their deployment into real critical systems.
Unfortunately, the current maturity of research is still far from guaranteeing a safe, secure and robust operation of ML algorithms in many domains. Therefore, this track calls for contributions that aim at making a step towards a safe, secure and robust operation of ML components through (non-exhaustive list):
the definition of architectural patterns (e.g., safety monitors or safety wrappers), software mechanisms, model-based analyses, and metrics aiming at a safe operation of ML algorithms;
the proposal or experimental evaluation of defenses against adversarial attacks or any potential threat to ML algorithms themselves;
techniques to make ML algorithms robust against unknown, out-of-distribution data, and their evaluation in simulated environments or in the wild;
methods for explainable AI, their evaluation, comparison and applicability to critical systems;
frameworks or mechanisms to precisely compute the confidence in the prediction of ML algorithms, and use them to build a safe, secure or robust ML-based component;
methodologies or data-driven processes that aim at guiding the integration of ML algorithms in critical systems such that safety and security requirements of the encompassing systems can be guaranteed.
To be announced in late fall.
September 20, 2024: October 13th, 2024 (extended twice!) Submission of regular papers and SRC research abstracts
October 30, 2024: Notification of paper/SRC acceptance/rejection
November 29, 2024: Camera-ready copies of accepted papers/SRC
December 6, 2024: Author registration due date
March 31 - April 4, 2025: Conference in Catania, Sicily, Italy
SAC (and thus S2RAI) accepts to types of submissions: regular papers and SRC Abstracts. The review process is double-blind: please prepare your paper accordingly. You can download the official Autor Kit from here (contains MS Word and Latex-Overleaf templates).
Regular papers: the total number of pages allowed with your registration without any extra page fee is eight (8). See the SAC 2025 website registration page for additional page charges. A maximum of 10 (first 8 pages no extra fees, 2 extra pages with fees) is allowed for each regular paper.
Student Research Track (SRC) Abstracts: the total number of pages allowed with your registration is four (4). No extra pages. The conference provides travel grants for PhD students, check here for further information.
Note that those page limits include references.
Regular papers: see here
SRC papers: see here
Paper registration is required, allowing the inclusion of the paper/poster in the conference proceedings. An author or a proxy attending SAC MUST present the paper paying a full conference fee. This is a requirement for the paper/poster to be included in the ACM digital library. No-show of registered papers and posters will result in excluding them from the ACM digital library.
Jeremie Guiochet (LAAS CNRS, University of Toulouse, France)
Antonio Pecchia (University of Sannio, Italy)
Maura Pintor (University of Cagliari, Italy)
Tommaso Zoppi (University of Trento, Italy)
Should you have any questions, please mail tommaso<dot>zoppi<at>unitn<dot>it
Ordered by Surname/Family Name in descending oder
Giuseppina Andresini (University of Bari Aldo Moro, Bari, Italy)
Muhammad Atif (University of Florence, Florence, Italy)
Cornelius Buerkle (Intel, Karlsruhe, Germany)
Simon Burton (University of York, York, UK)
Joao Campos (University of Coimbra, Coimbra, Portugal)
Javier Carnerero Cano (Imperial College London, London, UK)
Antonio Casimiro (University of Lisbon, Lisbon, Portugal)
Daniel Casini (Scuola Superiore Sant'Anna, Pisa, Italy)
Valentina Casola (Università degli Studi di Napoli Federico II, Naples, Italy)
Marta Catillo (University of Sannio, Benevento, Italy)
Zakaria Chihani (CEA, France)
Andrew Cullen (University of Melbourne, Melbourne, Australia)
Salvatore D'Antonio (Università degli Studi di Napoli Parthenope, Naples, Italy)
Francesco Flammini (IDSIA USI-SUPSI / Mälardalen University, Mälardalen, Sweden)
Lydia Gauerhof (Robert Bosch GmbH, Munich, Germany)
Simos Gerasimou (University of York, York, UK)
Joris Guerin (Espace-Dev, IRD, Montpellier, France)
Tom Haider (Fraunhofer IKS, Munich, Germany)
Benjamin Herd (Fraunhofer IKS, Munich, Germany)
Nico Hochgeschwender (Universitat Bremen, Bremen, Germany)
Sanghyun Hong (Oregon State University, Corvallis, US)
Nektaria Kaloudi (SINTEF Digital, Norway)
Bettina Könighofer (TU Wien, Wien, Austria)
Raphael Labaca-Castro (SandboxAQ, US)
Guanpeng Li (University of Iowa, Iowa - US)
Fumio Machida (University of Tsukuba, Tsukuba, Japan)
Leonardo Montecchi (Norwegian University of Science and Technology, Trondheim, Norway)
Chokri Mraidha (CEA LIST, Paris-Saclay University, France)
Azqa Nadeem (University of Twente, Enschede, NL)
Fabian Oboril (Intel Labs Europe, Kalsruhe, Germany)
Ganesh Pai (KBR / NASA Ames Research Center, US)
Karthik Pattabiraman (University of British Columbia, Vancouver, Canada)
Gabriel Pedroza (Ansys, Paris, France)
Irdin Pekaric (University of Liechtenstein, Liechtenstein)
Antonio Repola (University of Sannio, Benevento, Italy)
Giulio Rossolini (Scuola Superiore Sant'Anna, Pisa, Italy)
Altair Santin (Pontifical Catholic University of Parana, Curitiba, BR)
Burcu Sayin (University of Trento, Povo, Italy)
Marco Vieira (University of North Carolina at Charlotte, Cherlotte, US)
Xingyu Zhao (University of Warwick, Coventry, UK)
At the past edition of S2RAI@SAC24, 7 papers were accepted for presentation.
Data Poisoning Detection in Federated Learning (Denise-Phi Khuu, Michael Sober, Dominik Kaaser, Mathias Fischer and Stefan Schulte)
Validation of Safety Metrics for Object Detectors in Autonomous Driving (Andreas Rønnestad, Andrea Ceccarelli and Leonardo Montecchi)
Can you trust your Agent? The Effect of Out-of-Distribution Detection on the Safety of Reinforcement Learning Systems (Tom Haider, Karsten Roscher, Benjamin Herd, Felippe Schmoeller Roza and Simon Burton)
Can you trust your ML metrics? Using Subjective Logic to determine the true contribution of ML metrics for safety (Benjamin Herd and Simon Burton)
Multi-Confederated Learning: Inclusive Non-IID Data handling with Decentralized Federated Learning (Michael Duchesne, Kaiwen Zhang and Talhi Chamseddine)
Understanding the Process of Data Labeling in Cybersecurity (Tobias Braun, Irdin Pekaric and Giovanni Apruzzese)
Deceptive Skies: Leveraging GANs for Drone Sensor Data Falsification (Mehmed Uludag, Maryna Veksler, Yasin Yilmaz and Kemal Akkaya)