人工智慧系統的安全治理，價值對齊與驗測
人工智慧系統的發展自 2022 年後開始爆發性成長，而快速滲透進各種產業的應用場景。但是人工智慧在經濟發展與生產力提升之餘，產官學界也開始深度關切人工智慧的進展，逐漸朝向超級智慧 (SuperIntelligence) 迫近之時，吾人是否有足夠的方法來克服人工智慧系統帶來的諸項風險。
目前國際間對人工智慧治理除了着重在規範治理之外，亦有人工智慧對齊與驗測的方法來緩解人工智慧系統的各類安全與可信賴風險。國際趨勢如何發展與我國如何對應，將深切影響我國人工智慧產業的未來。
TOPIC / TRACK
AI Security & Safety Forum
LOCATION
Taipei Nangang Exhibition Center, Hall 2
7F 701B
LEVEL
Intermediate Intermediate sessions focus on
cybersecurity
architecture, tools, and practical applications, ideal for
professionals with a basic understanding of
cybersecurity.
SESSION TYPE
Breakout Session
LANGUAGE
Chinese
SUBTOPIC
AI Safety
AI Security
Responsible AI
CYBERSEC 2025 uses cookies to provide you with the best user experience possible. By continuing to use this site, you agree to the terms in our Privacy Policy 。