Abstract is missing.
- Impossibility of Unambiguous Communication as a Source of Failure in AI SystemsWilliam Howe, Roman Yampolskiy. [doi]
- Chess as a Testing Grounds for the Oracle Approach to AI SafetyJames D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong. [doi]
- Measuring Ensemble Diversity and Its Effects on Model RobustnessLena Heidemann, Adrian Schwaiger, Karsten Roscher. [doi]
- Uncontrollability of Artificial IntelligenceRoman Yampolskiy. [doi]
- Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational ProfilesXingyu Zhao, Wei Huang, Alec Banks, Victoria Cox, David Flynn, Sven Schewe, Xiaowei Huang 0001. [doi]
- Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range SupervisionFlorian Geissler, Syed Qutub, Sayanta Roychowdhury, Ali Asgari, Yang Peng, Akash Dhamasia, Ralf Graefe, Karthik Pattabiraman, Michael Paulitsch. [doi]
- Domain Shifts in Reinforcement Learning: Identifying Disturbances in EnvironmentsTom Haider, Felippe Schmoeller Roza, Dirk Eilers, Karsten Roscher, Stephan Günnemann. [doi]
- Towards Robust Perception Using Topological InvariantsRomie Banerjee, Feng Liu, Pei Ke. [doi]
- Using Complementary Risk Acceptance Criteria to Structure Assurance Cases for Safety-Critical AI ComponentsMichael Klaes, Rasmus Adler, Lisa Jöckel, Janek Groß, Jan Reich. [doi]
- On the Differences between Human and Machine IntelligenceRoman Yampolskiy. [doi]
- A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural NetworksChristopher Lazarus, Mykel J. Kochenderfer. [doi]
- Artificial Intelligence for Future Skies: On-going Standardization Activities to Build the Next Certification/Approval Framework for Airborne and Ground Aeronautic ProductsChristophe Gabreau, Béatrice Pesquet-Popescu, Fateh Kaakai, Baptiste Lefèvre. [doi]
- Coyote: A Dataset of Challenging Scenarios in Visual Perception for Autonomous VehiclesSuruchi Gupta, Ihsan Ullah, Michael Madden. [doi]
- Applying Strategic Reasoning for Accountability Ascription in Multiagent TeamsVahid Yazdanpanah, Sebastian Stein 0001, Enrico Gerding, Nicholas R. Jennings. [doi]
- An Adversarial Attacker for Neural Networks in Regression ProblemsKavya Gupta, Jean-Christophe Pesquet, Béatrice Pesquet-Popescu, Fateh Kaakai, Fragkiskos D. Malliaros. [doi]
- Deep Neural Network Loses Attention to Adversarial ImagesShashank Kotyan, Danilo Vasconcellos Vargas. [doi]
- Socio-technical co-Design for Accountable Autonomous SoftwareAyan Banerjee, Imane Lamrani, Katina Michael, Diana M. Bowman, Sandeep K. S. Gupta. [doi]
- Epistemic Defenses against Scientific and Empirical Adversarial AI AttacksNadisha-Marie Aliman, Leon Kester. [doi]