세미나

[세미나] The Bright and Dark Sides of Computer Vision & Machine Learning: Challenges and Opportunities for Privacy and Security
작성일2019-10-29

o 일정 및 장소:

- 일시: 2019.11.1(금) 14:00~

- 장소: N1건물 112호

==============================

 

Title: The Bright and Dark Sides of Computer Vision & Machine Learning: Challenges and Opportunities for Privacy and Security     


 
Abstract: 
Today, vast amounts of visual information is collected and often also shared online. Such images and videos can contain various types of privacy-sensitive information that can nowadays be extracted automatically at a large scale, posing a steadily growing threat to users' privacy. I'll give an overview of our efforts towards understanding and controlling privacy in visual information as well as working towards our overall vision of a Visual Privacy Advisor. 

More generally speaking, we have seen a quick adoption of machine learning technology in a broad range of application scenarios. With such broad deployment, these approaches become part of the attack surface of modern IT infrastructures and therefore new privacy and security risks emerge. Hence, we research attack vectors and defenses of such intelligent systems built on AI and machine learning technology. In particular, I will talk about our latest work on membership inference and model stealing.

Furthermore, the latest generative models have shown to be capable of synthesizing photo-realistic data. This challenges the authenticity of and trust in information. I'll present our latest work on detecting fake image and attributing them to different sources.


Bio: 
Mario Fritz is faculty member at the CISPA Helmholtz Center for Information Security and a leading scientist of the Helmholtz Medical Security, Privacy, and AI Research Center. Before, he was senior researcher and research group head at the Max Planck Institute for Informatics, DE, and PostDoc at the International Computer Science Institute and UC Berkeley, US. He did his PhD at the TU Darmstadt, DE (with distinction). He served as Area Chair for major computer vision conferences (ECCV, ICCV), is associate editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and member of the ACM Europe Technical Policy Committee Europe. He has co-authored over 90 publications — more than 50 in top-tier journals (IJCV, TPAMI) and conferences (CVPR, ICCV, ECCV, IROS, ICRA, NeurIPS, AAAI, ICLR, NDSS, USENIX Security). 

 

for more information and latest work visit:
homepage: https://fritz.cispa.saarland
google scholar: https://scholar.google.de/citations?user=4V1nNm4AAAAJ&hl=en&oi=ao
dblp: https://dblp.uni-trier.de/pers/hd/f/Fritz:Mario