Abstract is missing.
- AI for Safety: How to use Explainable Machine Learning Approaches for Safety AnalysesIwo Kurzidem, Simon Burton 0001, Philipp Schleiss. [doi]
- An open source perspective on AI and alignment with the EU AI ActDiego Calanzone, Andrea Coppari, Riccardo Tedoldi, Giulia Olivato, Carlo Casonato. [doi]
- PerCBA: Persistent Clean-label Backdoor Attacks on Semi-Supervised Graph Node ClassificationXiao Yang, Gaolei Li, Chaofeng Zhang, Meng Han, Wu Yang. [doi]
- Weight-based Semantic Testing Approach for Deep Neural NetworksAmany Alshareef, Nicolas Berthier, Sven Schewe, Xiaowei Huang 0001. [doi]
- Fear Field: Adaptive constraints for safe environment transitions in Shielded Reinforcement LearningHaritz Odriozola-Olalde, Nestor Arana-Arexolaleiba, Maider Zamalloa, Jon Pérez-Cerrolaza, Jokin Arozamena-Rodríguez. [doi]
- Distribution-restrained Softmax Loss for the Model RobustnessChen Li, Hao Wang, Jinzhe Jiang, Xin Zhang, Yaqian Zhao, Weifeng Gong. [doi]
- Risk-sensitive Actor-free Policy via Convex OptimisationRuoqi Zhang, Jens Sjölund. [doi]
- Unsupervised Unknown Unknown Detection in Active LearningPrajit T. Rajendran, Huáscar Espinoza, Agnès Delaborde, Chokri Mraidha. [doi]
- Diffusion Denoised Smoothing for Certified and Adversarial Robust Out Of DistributionNicola Franco, Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Stephan Günnemann. [doi]
- Empirical Optimal Risk to Quantify Model Trustworthiness for Failure DetectionShuang Ao, Stefan Rueger, Advaith Siddharthan. [doi]