![](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@IJCAI 2022: Vienna, Austria
- Gabriel Pedroza, Xin Cynthia Chen, José Hernández-Orallo, Xiaowei Huang, Huáscar Espinoza, Richard Mallah, John A. McDermid, Mauricio Castillo-Effen:
Proceedings of the Workshop on Artificial Intelligence Safety 2022 (AISafety 2022) co-located with the Thirty-First International Joint Conference on Artificial Intelligence and the Twenty-Fifth European Conference on Artificial Intelligence (IJCAI-ECAI-2022), Vienna, Austria, July 24-25, 2022. CEUR Workshop Proceedings 3215, CEUR-WS.org 2022
Session 1: AI Ethics: Fairness, Bias, and Accountability
- Mattias Brännström, Andreas Theodorou, Virginia Dignum:
Let it RAIN for Social Good. - Palak Malhotra, Amita Misra:
Accountability and Responsibility of Artificial Intelligence Decision-making Models in Indian Policy Landscape. - Iris Dominguez-Catena, Daniel Paternain, Mikel Galar:
Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognition.
Session 2: Short Presentations - Safety Assessment of AI-enabled systems
- Yi Qi, Philippa Ryan Conmy, Wei Huang, Xingyu Zhao, Xiaowei Huang:
A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems. - Jérôme Hugues, Daniela Cancila:
Increasingly Autonomous CPS: Taming Emerging Behaviors from an Architectural Perspective. - Julien Girard-Satabin, Michele Alberti, François Bobot, Zakaria Chihani, Augustin Lemesle:
CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness.
Session 3: Machine Learning for Safety-critical AI
- Patrick Feifel, Benedikt Franke, Arne P. Raulf, Friedhelm Schwenker, Frank Bonarens, Frank Köster:
Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection. - Daniel Scholz, Florian Hauer, Klaus Knobloch, Christian Mayr:
Improvement of Rejection for AI Safety through Loss-Based Monitoring.
Session 4: Short Presentations - ML Robustness, Criticality and Uncertainty
- Georg Siedel, Silvia Vock, Andrey Morozov, Stefan Voß:
Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers. - Prajit T. Rajendran, Guillaume Ollier, Huáscar Espinoza, Morayo Adedjouma, Agnès Delaborde, Chokri Mraidha:
Safety-aware Active Learning with Perceptual Ambiguity and Criticality Assessment. - Juan Shu, Bowei Xi, Charles A. Kamhoua:
Understanding Adversarial Examples Through Deep Neural Network's Classification Boundary and Uncertainty Regions.
Session 5: AI Robustness, Generative Models and Adversarial Learning
- Adrien Le-Coz, Stéphane Herbin, Faouzi Adjed:
Leveraging generative models to characterize the failure conditions of image classifiers. - Svetlana Pavlitskaya, Bianca-Marina Codau, J. Marius Zöllner:
Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection. - Jonghu Jeong, Minyong Cho, Philipp Benz, Jinwoo Hwang, Jeewook Kim, Seungkwan Lee, Taehoon Kim:
Privacy Safe Representation Learning via Frequency Filtering Encoder. - Pol Labarbarie, Adrien Chan-Hon-Tong, Stéphane Herbin, Milad Leyli-Abadi:
Benchmarking and deeper analysis of adversarial patch attack on object detectors.
Session 6: AI Accuracy, Diversity, Causality and Optimization
- Cedrique Rovile Njieutcheu Tassi, Jakob Gawlikowski, Auliya Unnisa Fitri, Rudolph Triebel:
The impact of averaging logits over probabilities on ensembles of neural networks. - Michal Filipiuk, Vasu Singh:
Exploring Diversity in Neural Architectures for Safety. - Mohammad Kachuee, Sungjin Lee:
Constrained Policy Optimization for Controlled Contextual Bandit Exploration. - Francis Rhys Ward, Francesco Belardinelli, Francesca Toni:
A causal perspective on AI deception in games.
![](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.