Picture Archiving and Communication System (PACS) servers are crucial for managing patient imaging data in medical institutions. This presentation explores the essential functions of PACS servers and the structure of DICOM (Digital Imaging and Communications in Medicine) files, emphasizing the importance of unique identifiers.

We discuss the processing and transmission of DICOM files using various protocols and uncover significant privacy and security risks associated with exposed PACS servers and DICOM files on the internet.

Our research has identified multiple vulnerabilities in PACS servers, including use-after-free, stack-based buffer overflow, and path traversal, which could disrupt medical operations or result in the deletion of patient data.

The goal of this presentation is to raise security awareness and provide practical mitigation strategies for medical staff and server developers to protect sensitive medical data.

Using artificial intelligence to generate IPS rules has excellent potential to enhance network security, especially in detecting complex and evolving threats. However, it is not a panacea. AI models can generate too broad or specific rules, leading to false positives (over-alarming) or false negatives (missing threats). Many AI-generated rules may degrade the performance of IDS, especially in high-throughput networks. Based on the evaluation, a hybrid approach combining the strengths of AI and human expertise may be the most suitable approach for generating AI-driven IPS rules.