All Sessions：

In this session, we will explore the world of large language models (LLMs) from a hacker's perspective. By deploying Ollama locally as an attacker, we will simulate automated attacks targeting various systems using LLMs. The live demonstration aims to highlight the critical importance of LLM security. Participants will experience firsthand how LLMs can be weaponized and will engage in discussions on strategies to defend against such threats. This will emphasize the need for robust security measures in AI-driven environments. Using HackingBuddyGPT as a prototype, combined with Ollama deployed locally, we will demonstrate automated attacks on target systems. Regardless of whether the attacks succeed, this research will reveal how LLMs, while offering convenience, can also be exploited as tools for malicious hacking. This serves as a warning to developers, researchers, and others, raising awareness of the importance of LLM security.

Latest Applications of Large Language Models: AI Fortune Interpretation, AI Content Creation, AI Oracle Explanation, AI Scripture Interpretation, AI Customer Service Latest Applications of Image Analysis Algorithms: AI People Counting System, AI Guardian System (Fire Detection, Smoke Detection, Anti-theft) 最新大型語言模型應用：AI 解籤、AI 小編、AI 解鸞文、AI 解經文、AI 客服 最新影像分析演算法應用：AI 人流系統、AI 門神系統 (防火、防煙、防盜)

Non-programmers are now using AI to write code and automate tasks that make their daily work easier. I've been running study groups ([blog.gaiconf.com 連結]) to help them learn how to do this. In my talk, I want to share some of the incredible things these non-engineers have been able to build with the help of AI.

Multimodal AI is revolutionizing traditional manufacturing by equipping manufacturing equipment with stronger perception and decision-making abilities. This enables automation and intelligence in production processes, allowing enterprises to create more resilient and efficient smart factories. 隨著多模態 AI 技術的成熟，傳統製造業正在經歷一場深刻的轉型。多模態 AI 能夠賦予製造設備更強的感知能力和決策能力，實現生產過程的自動化和智能化。透過多模態 AI，企業能夠打造更具彈性、更具效率的智慧工廠，從而提升市場競爭力。

Exploring how AI-driven visual inspection platforms and generative image technology enable fast and high-precision defect detection, while boosting production efficiency. This session will focus on the role of these cutting-edge technologies in accelerating digital transformation within the manufacturing industry. 探討如何透過 AI 視覺檢測平台與生成圖像實現快速與高精度瑕疵檢測和生產效率提升，助力製造業數位轉型

Eval-Driven-Development (EDD) is a method for developing LLM-based apps guided by task-specific evaluations, including dataset synthesis, evaluation metric design, and automatic prompt optimization. In this short talk, I will quickly demonstrate this process.

This presentation will focus on the principles of multimodal language model technology and its applications in the healthcare field, demonstrating its extensive use through six different medical scenarios. Each scenario will be accompanied by a 30-second demo video, designed to give the audience a quick and immersive experience of these technologies' powerful capabilities in healthcare. We will begin by showcasing a chronic disease management Q&A system for dementia knowledge. This system is presented in a website format and provides accurate, real-time medical information through a language model, helping users better understand disease-related information. Following this, we will introduce a Line Chatbot for remote diabetes care, which facilitates intelligent Q&A between patients and healthcare providers, offering immediate medical support to diabetes patients. In the area of emotional companionship, we will share a TVBS interview video demonstrating how an emotional companion QA robot uses language models for question-answering, offering psychological support and enhancing patients' emotional well-being. Additionally, we will demonstrate a digital interaction display for standardized dental patient interactions, where AI automates assessments to enhance the interactivity and effectiveness of dental education. For image processing applications, we will introduce an X-ray dental image report generation system that assists doctors in automatically generating dental imaging reports, significantly improving medical efficiency. Lastly, we will present a text-to-dental 3D image generation technology that converts text input into 3D images, applied in the development of VR imaging for surgical planning, showcasing cutting-edge technologies in dental surgery. Through these demo videos, we will guide the audience to a deeper understanding of how multimodal language model technology plays a key role in various healthcare scenarios, highlighting its significance in the future development of medical technology.

The intersection of LLM and privacy-preserving techniques is an emerging research field, particularly relevant for domain-specific applications. There is increasing interest in methodologies that enable collaborative or multi-tenant training and inference while addressing both trust and efficiency concerns. In this talk, I will give a high-level tutorial on several cryptographic techniques that may help the audience better understand the state-of-the-art research in the area of secure AI inference.

Artificial Intelligence (AI) is rapidly transforming the landscape of technology and society. This presentation will delve into the profound impact of AI development on both individual users and professionals across various industries. *AI PC For individual users, as the leader in high-performance Gaming PCs, MSI is integrating AI technology into its innovations, such as a self-developed small language model preloaded in MSI AI PCs. This model supports offline generative AI capabilities, addressing user needs for data privacy protection and real-time responsiveness. *AI Server and AI AMR Robot For enterprise users, MSI’s AI server platforms empower businesses to achieve efficiency gains while handling more compute-intensive workloads. MSI’s AI AMR Robot solutions showcase MSI's commitment to innovation in the fields of smart manufacturing and automation. We will explore how AI is revolutionizing the way we work, live, and interact, and discuss the challenges and opportunities presented by this transformative technology.

In recent years, the rapid development of artificial intelligence (AI) hardware and software technologies has made the development and utilization of data to train AI models a significant topic. Training AI models not only requires clean domain data and expertise but is also closely related to programming skills. Since AI models can be applied across various industries, familiarity with industry-specific knowledge is very important. This lecture will introduce Quanta Computer's AI Medical Platform (QOCA aim), showcasing how AI and IT experts collaborate with medical specialists from various fields to fast develop more AI models applicable to different industries. These AI models are then quickly integrated into business operations to help enhance efficiency and service quality across sectors.