Abstract: TBD

• Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection - Nicola Franco, Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Stephan Günnemann

• Unsupervised Unknown Unknown Detection in Active Learning - Prajit T. Rajendran, Huascar Espinoza, Agnes Delaborde, Chokri Mraidha

> Debate Panel - Session Discussants: Presenters and Session Chair.

• PerCBA: Persistent Clean-label Backdoor Attacks on Semi-Supervised Graph Node Classification – Xiao Yang, Gaolei Li, Chaofeng Zhang, Meng Han, Wu Yang

• Distribution-restrained Softmax Loss for the Model Robustness - Chen Li, Hao Wang, Jinzhe Jiang, Xin Zhang, Yaqian Zhao, Weifeng Gong

• Fear Field: Adaptive constraints for safe environment transitions in Shielded Reinforcement Learning - Haritz Odriozola-Olalde, Nestor Arana-Arexolaleiba, Maider Zamalloa, Jon Perez-Cerrolaza, Jokin Arozamena-Rodríguez

> Debate Panel - Session Discussants: Presenters and Session Chair.

• An open source perspective on AI and alignment with the EU AI Act - Diego Calanzone, Andrea Coppari, Riccardo Tedoldi, Giulia Olivato, Carlo Casonato

• ​

> Debate Panel - Session Discussants: Presenters and Session Chair.

The explosion in the performance of Machine Learning (ML) and the potential of its applications are strongly encouraging us to consider its use in industrial systems, including for critical functions such as decision-making in autonomous systems. While the AI community is well aware of the need to ensure the trustworthiness of AI-based applications, it is still leaving too much to one side the issue of safety and its corollary, regulation and standards, without which it is not possible to certify any level of safety, whether the systems are slightly or very critical.
The process of developing and qualifying safety-critical software and systems in regulated industries such as aerospace, nuclear power stations, railways or automotive industry has long been well rationalized and mastered. They use well-defined standards, regulatory frameworks and processes, as well as formal techniques to assess and demonstrate the quality and safety of the systems and software they develop. However, the low level of formalization of specifications and the uncertainties and opacity of machine learning-based components make it difficult to validate and verify them using most traditional critical systems engineering methods. This raises the question of qualification standards, and therefore of regulations adapted to AI. With the AI Act, the European Commission has laid the foundations for moving forward and building solid approaches to the integration of AI-based applications that are safe, trustworthy and respect European ethical values. The question then becomes “How can we rise to the challenge of certification and propose methods and tools for trusted artificial intelligence?”.

• Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection - Shuang Ao, Stefan Rueger, Advaith Siddharthan.

• Weight-based Semantic Testing Approach for Deep Neural Networks - Amany Alshareef, Nicolas Berthier, Sven Schewe and Xiaowei Huang

• AI for Safety: How to use Explainable Machine Learning Approaches for Safety Analyses – Iwo Kurzidem, Simon Burton, Philipp Schleiss

> Debate Panel - Session Discussants: Presenters and Session Chair.