![](https://dblp1.uni-trier.de/img/logo.ua.320x120.png)
![](https://dblp1.uni-trier.de/img/dropdown.dark.16x16.png)
![](https://dblp1.uni-trier.de/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp1.uni-trier.de/img/search.dark.16x16.png)
![search dblp](https://dblp1.uni-trier.de/img/search.dark.16x16.png)
default search action
AISafety/SafeRL@IJCAI 2023: Macao, SAR, China
- Gabriel Pedroza, Xiaowei Huang, Xin Cynthia Chen, Andreas Theodorou, Huáscar Espinoza, Nikolaos Matragkas, José Hernández-Orallo, Mauricio Castillo-Effen, Richard Mallah, John A. McDermid, David M. Bossens, Bettina Könighofer, Sebastian Tschiatschek, Anqi Liu:
Proceedings of the IJCAI-23 Joint Workshop on Artificial Intelligence Safety and Safe Reinforcement Learning (AISafety-SafeRL 2023) co-located with the 32nd International Joint Conference on Artificial Intelligence(IJCAI2023), Macau, China, August 21-22, 2023. CEUR Workshop Proceedings 3505, CEUR-WS.org 2023
Session 1: Robustness of AI via OoD and Unknown-Unknowns Dectection
- Nicola Franco, Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Stephan Günnemann:
Diffusion Denoised Smoothing for Certified and Adversarial Robust Out Of Distribution. - Prajit T. Rajendran, Huáscar Espinoza, Agnès Delaborde, Chokri Mraidha:
Unsupervised Unknown Unknown Detection in Active Learning.
Session 2: AI Robustness, Adversarial Attacks and Reinforcemnt Learning
- Xiao Yang, Gaolei Li, Chaofeng Zhang, Meng Han, Wu Yang:
PerCBA: Persistent Clean-label Backdoor Attacks on Semi-Supervised Graph Node Classification. - Chen Li, Hao Wang, Jinzhe Jiang, Xin Zhang, Yaqian Zhao, Weifeng Gong:
Distribution-restrained Softmax Loss for the Model Robustness. - Haritz Odriozola-Olalde, Nestor Arana-Arexolaleiba, Maider Zamalloa, Jon Pérez-Cerrolaza, Jokin Arozamena-Rodríguez:
Fear Field: Adaptive constraints for safe environment transitions in Shielded Reinforcement Learning.
Session 3: AI Governance and Policy/Value Alignment
- Diego Calanzone, Andrea Coppari, Riccardo Tedoldi, Giulia Olivato, Carlo Casonato:
An open source perspective on AI and alignment with the EU AI Act.
Session 4: Safe RL
- Ruoqi Zhang, Jens Sjölund:
Risk-sensitive Actor-free Policy via Convex Optimisation.
Session 5: AI Trustworthiness, Explainability and Testing
- Shuang Ao, Stefan Rueger, Advaith Siddharthan:
Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection. - Iwo Kurzidem, Simon Burton, Philipp Schleiss:
AI for Safety: How to use Explainable Machine Learning Approaches for Safety Analyses.
![](https://dblp1.uni-trier.de/img/cog.dark.24x24.png)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.