Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSafeAI@AAAI 2019: Honolulu, Hawaii, USA
- Huáscar Espinoza, Seán Ó hÉigeartaigh, Xiaowei Huang, José Hernández-Orallo, Mauricio Castillo-Effen:
Workshop on Artificial Intelligence Safety 2019 co-located with the Thirty-Third AAAI Conference on Artificial Intelligence 2019 (AAAI-19), Honolulu, Hawaii, January 27, 2019. CEUR Workshop Proceedings 2301, CEUR-WS.org 2019
Invited Talk
- Peter Eckersley:
Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function).
Session 1: Safe Planning and Operation of Autonomous Systems
- Sandhya Saisubramanian, Shlomo Zilberstein:
Minimizing the Negative Side Effects of Planning with Reduced Models. - Shih-Yun Lo, Shani Alkoby, Peter Stone:
Robust Motion Planning and Safety Benchmarking in Human Workspaces. - Mark O. Riedl, Brent Harrison:
Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization.
Session 2: New Paradigms in AI and AGI Safety
- Lê Nguyên Hoang:
Towards Robust End-to-End Alignment. - Gopal P. Sarma, Adam Safron, Nick J. Hay:
Integrative Biological Simulation, Neuropsychology, and AI Safety.
Session 3: Safety in Automated Driving
- Philip Koopman, Frank Fratrik:
How Many Operational Design Domains, Objects, and Events? - Saasha Nair, Sina Shafaei, Stefan Kugele, Mohd Hafeez Osman, Alois C. Knoll:
Monitoring Safety of Autonomous Vehicles with Crash Prediction Networks.
Session 4: Safety-Related AI Requirements and Characteristics
- Alec Banks, Rob Ashmore:
Requirements Assurance in Machine Learning. - José Hernández-Orallo, Fernando Martínez-Plumed, Shahar Avin, Seán Ó hÉigeartaigh:
Surveying Safety-relevant AI Characteristics.
Session 5: Adversarial Machine Learning
- Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian M. Molloy, Biplav Srivastava:
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering. - Xin Liu, Huanrui Yang, Ziwei Liu, Linghao Song, Yiran Chen, Hai Li:
DPATCH: An Adversarial Patch Attack on Object Detectors. - Katja Auernhammer, Ramin Tavakoli Kolagari, Markus Zoppelt:
Attacks on Machine Learning: Lurking Danger for Accountability.
Short Poster Papers
- Frank Rudzicz, P. Alison Paprica, Marta Janczarski:
Towards international standards for evaluating machine learning. - Kacper Sokol, Peter A. Flach:
Counterfactual Explanations of Machine Learning Predictions: Opportunities and Challenges for AI Safety. - Bence Cserna, William J. Doyle, Tianyi Gu, Wheeler Ruml:
Safe Temporal Planning for Urban Driving. - Yi Zeng, Enmeng Lu, Cunqing Huangfu:
Linking Artificial Intelligence Principles. - Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir:
Emergence of Addictive Behaviors in Reinforcement Learning Agents. - Philip Amortila, Marc G. Bellemare, Prakash Panangaden, Doina Precup:
Temporally Extended Metrics for Markov Decision Processes. - Tao Li, Lei Lin, Siyuan Gong:
AutoMPC: Efficient Multi-Party Computation for Secure and Privacy-Preserving Cooperative Control of Connected Autonomous Vehicles. - Saerom Park, Jaewook Lee, Jung Hee Cheon, Juhee Lee, Jaeyun Kim, Junyoung Byun:
Security-preserving Support Vector Machine with Fully Homomorphic Encryption. - Huanrui Yang, Jingchi Zhang, Hsin-Pai Cheng, Wenhan Wang, Yiran Chen, Hai Li:
Bamboo: Ball-Shape Data Augmentation Against Adversarial Attacks from All Directions.
a service of 
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.
last updated on 2024-08-23 18:34 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
