AISafety 2024
IJCAI 2024 Workshop on Artificial Intelligence Safety

Table of Contents

• Preface
  Summary: There were 11 papers submitted for peer-review to this workshop. Out of these, 8 papers were accepted for this volume, all 8 as regular papers.

Session 1: AI Safety Assessment: Validation Methods and Techniques

• ReLESS: A Framework for Assessing Safety in Deep Learning Systems
  Anita Raja, Nan Jia, Raffi Khatchadourian
• Enhancing Autonomous Vehicle Safety through N-version Machine Learning Systems
  Qiang Wen, Júlio Mendonça, Fumio Machida, Marcus Völp

Session 2: AI Robustness: Adversarial Learning and Security/Privacy

• Hyper-parameter Tuning for Adversarially Robust Models
  Pedro Mendes, Paolo Romano, David Garlan
• Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC
  Ke Lin, Yasir Glani, Ping Luo

Session 3: Safety of Generative AI: OoD and Human vs Machine Generative Detection

• Detecting out-of-distribution text using topological features of transformer-based language models
  Andres Pollano, Anupam Chaudhuri, Anj Simmons
• The Impact of Prompts on Zero-Shot Detection of AI-Generated Text
  Kouichi Sakurai, Kaito Taguchi, Yujie Gu

Session 4: AI Robustness: Resilience to Noise and Soft Errors

• Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models
  Qutub Syed, Michael Paulitsch, Karthik Pattabiraman, Korbinian Hagn, Fabian Oboril, Cornelius Buerkle, Kay-Ulrich Scholl, Gereon Hinz, Alois Knoll
• Neural Vicinal Risk Minimization: Noise-robust Distillation for Noisy Labels
  Hyounguk Shon, Seunghee Koh, Yunho Jeon, Junmo Kim