


default search action
AISafety@IJCAI 2024: Jeju, Korea
- Gabriel Pedroza, Xiaowei Huang, Xin Cynthia Chen, Fabio Arnez, Huáscar Espinoza, José Hernández-Orallo, Mauricio Castillo-Effen, Richard Mallah, John A. McDermid, Andreas Theodorou:
Proceedings of the IJCAI 2024 Workshop on Artificial Intelligence Safety (AISafety 2024) co-located with the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), Jeju, Korea, August 4, 2024. CEUR Workshop Proceedings 3856, CEUR-WS.org 2024
Session 1: AI Safety Assessment: Validation Methods and Techniques
- Anita Raja, Nan Jia, Raffi Khatchadourian:
ReLESS: A Framework for Assessing Safety in Deep Learning Systems. - Qiang Wen, Júlio Mendonça, Fumio Machida, Marcus Völp:
Enhancing Autonomous Vehicle Safety through N-version Machine Learning Systems.
Session 2: AI Robustness: Adversarial Learning and Security/Privacy
- Pedro Mendes, Paolo Romano, David Garlan:
Hyper-parameter Tuning for Adversarially Robust Models. - Ke Lin, Yasir Glani, Ping Luo:
Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC.
Session 3: Safety of Generative AI: OoD and Human vs Machine Generative Detection
- Andres Pollano, Anupam Chaudhuri, Anj Simmons:
Detecting out-of-distribution text using topological features of transformer-based language models. - Kouichi Sakurai, Kaito Taguchi, Yujie Gu:
The Impact of Prompts on Zero-Shot Detection of AI-Generated Text.
Session 4: AI Robustness: Resilience to Noise and Soft Errors
- Syed Sha Qutub, Michael Paulitsch, Karthik Pattabiraman, Korbinian Hagn, Fabian Oboril, Cornelius Bürkle, Kay-Ulrich Scholl, Gereon Hinz, Alois Knoll:
Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models. - Hyounguk Shon, Seunghee Koh, Yunho Jeon, Junmo Kim:
Neural Vicinal Risk Minimization: Noise-robust Distillation for Noisy Labels.

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.