ijcai 2021 论文列表
Proceedings of the Workshop on Artificial Intelligence Safety 2021 co-located with the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI 2021), Virtual, August, 2021.
|
A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks.
On the Differences between Human and Machine Intelligence.
Epistemic Defenses against Scientific and Empirical Adversarial AI Attacks.
Socio-technical co-Design for Accountable Autonomous Software.
Chess as a Testing Grounds for the Oracle Approach to AI Safety.
Domain Shifts in Reinforcement Learning: Identifying Disturbances in Environments.
Uncontrollability of Artificial Intelligence.
Using Complementary Risk Acceptance Criteria to Structure Assurance Cases for Safety-Critical AI Components.
Artificial Intelligence for Future Skies: On-going Standardization Activities to Build the Next Certification/Approval Framework for Airborne and Ground Aeronautic Products.
Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision.
Coyote: A Dataset of Challenging Scenarios in Visual Perception for Autonomous Vehicles.
An Adversarial Attacker for Neural Networks in Regression Problems.
Deep Neural Network Loses Attention to Adversarial Images.
Measuring Ensemble Diversity and Its Effects on Model Robustness.
Towards Robust Perception Using Topological Invariants.
Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles.
Impossibility of Unambiguous Communication as a Source of Failure in AI Systems.
Applying Strategic Reasoning for Accountability Ascription in Multiagent Teams.
