Workshop on Robust Machine Learning Framework and Its Applications

This workshop focuses on robust machine learning framework and its applications in AI for logistics. The agenda includes invited talks, technical presentations, and opportunities for networking and collaboration.

Machine learning (ML) technologies have been widely adopted across mission-critical domains, including logistics, transportation, and industrial systems. While these systems offer significant benefits in efficiency and automation, their deployment also introduces substantial security and privacy risks, such as adversarial attacks, data leakage, and model exploitation. In response, a wide range of defense mechanisms—including robust training techniques, secure model inference, and privacy-preserving learning methods—have been proposed to mitigate these threats. At the same time, policymakers and regulatory bodies are establishing regulatory frameworks to enforce cybersecurity, privacy, and accountability requirements for AI systems. These developments highlight the urgent need for effective defense mechanisms, along with systematic evaluation methodologies and practical frameworks, to rigorously assess the security and reliability of ML systems and ensure their robustness, trustworthiness, and regulatory compliance in real-world deployments.