講者簡介：　Prof. Dr. Mario Fritz 是現任CISPA Helmholtz Center for Information Security (亥姆霍茲資訊安全中心，德國最大的資訊安全中心)的Leading Scientist、德國Saarland University的Honorary Professor (榮譽教授)、以及European Laboratory for Learning and Intelligent Systems (ELLIS, 由歐盟成立，跨越26個國家的學習和智慧系統實驗室)的主要負責人之一、更是目前歐盟及德國在人工智慧和資訊安全之發展政策制定過程中時常諮詢的對象。

 

演講主題： Trustworthy AI and A Cybersecurity Perspective on Large Language Models

演講摘要： As AI technology is getting increasingly mature, we see a broad deployment of AI in many application domains. However, this increases the demands on properties related to trustworthiness like robustness, privacy, transparency, accountability as well as explainability. In this talk, I will demonstrate what this means for future AI methodology and how we can reach those goals. Furthermore, for some of these properties like privacy and robustness, we can even provide guarantees so that we can ensure that these properties also hold in the future.
Besides trustworthiness of AI, misinformation and deepfakes are becoming a key concerns in terms of negative effects that AI can have on society. I'll discuss the larger ecosystem around misinformation and different approaches to mitigate these pressing issues in the future.
Finally, Large Language Models (LLMs) like GPT4 have demonstrated how AI deployment is reaching millions of users, which in turn puts a magnifying glass on some of the issues mentioned before. I'll demonstrate cybersecurity concerns and threats that emerge from the recent trend of application-integrated LLMs and AI assistants as well as sketch how future development will initiate completely new research challenges in this domain.

講者簡歷：Prof. Dr. Mario Fritz is a faculty at the CISPA Helmholtz Center for Information Security, an honorary professor at Saarland University, and a fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS). Until 2018, he led a research group at the Max Planck Institute for Computer Science. Previously, he was a PostDoc at the International Computer Science Institute (ICSI) and UC Berkeley after receiving his PhD from TU Darmstadt and studying computer science at FAU Erlangen-Nuremberg. His research focuses on trustworthy artificial intelligence, especially at the intersection of information security and machine learning. He is Associate Editor of the journal "IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and has published over 100 articles in top conferences and journals. Currently, he is coordinating the Network of Excellence in AI "ELSA -- European Lighthouse on Secure and Safe AI" that is funded by the EU in connects over 26 universities and research institutions across Europe ( elsa-ai.eu )