E-mail senden E-Mail Adresse kopieren

E-Mail

Adresse

Stuhlsatzenhaus 5
66123 Saarbrücken (Germany)

Kurzbiografie

Mario Fritz ist leitender Wissenschaftler am CISPA Helmholtz Zentrum für Informationssicherheit, Honorarprofessor an der Universität des Saarlandes und Fellow des European Laboratory for Learning and Intelligent Systems (ELLIS). Bis 2018 leitete er eine Forschungsgruppe am Max Planck Institute für Informatik. Zuvor war er PostDoc am International Computer Science Institute (ICSI) und an der UC Berkeley nach Promotion an der TU Darmstadt und Informatikstudium an der FAU Erlangen-Nürnberg. Seine Forschung fokussiert sich auf vertrauenswürdige künstliche Intelligenz insbesondere an der Schnittmenge von Informationssicherheit und maschinellem Lernen. Er ist Associate Editor der Zeitschrift "IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)", koordiniert das Helmholtz Projekt "Trustworthy Federated Data Analytics" und hat über 100 wissenschaftliche Artikel publiziert - 80 davon in den Top-Konferenzen und Zeitschriften.

CV: Letzte vier Stationen

Seit 2019
Professor an der Universität des Saarlandes
Seit 2018
Faculty am CISPA Helmholtz-Zentrum für Informationssicherheit
2011 - 2018
Senior Researcher, Max-Planck-Institut für Informatik
2008 - 2010
PostDoc International Computer Science Institue & UC Berkeley

Veröffentlichungen von Mario Fritz

Jahr 2023

Konferenz / Medium

USENIX
32nd USENIX Security Symposium32nd USENIX Security Symposium

Konferenz / Medium

USENIX-Security
USENIX SecurityUSENIX Security

Jahr 2022

Konferenz / Medium

NeurIPS
Proceedings of Machine Learning ResearchThirty-sixth Conference on Neural Information Processing Systems

Konferenz / Medium

USENIX-Security
USENIX Security Symposium (USENIX Security)USENIX Security Symposium (USENIX Security), 2022.

Konferenz / Medium

ICML
Proceedings of the 39th International Conference on Machine LearningInternational Conference on Machine Learning (ICML)

Konferenz / Medium

CVPR
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Conference on Computer Vision and Pattern Recognition

Konferenz / Medium

CVPR
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Conference on Computer Vision and Pattern Recognition

Konferenz / Medium

ICLR
International Conference on Learning RepresentationsThe Tenth International Conference on Learning Representations

Konferenz / Medium

ICLR
International Conference on Learning RepresentationsThe Tenth International Conference on Learning Representations

Konferenz / Medium

UNSPECIFIED
Proceedings of the Conference on Health, Inference, and LearningConference on Health, Inference, and Learning

Lehre von Mario Fritz

Winter 2021/22

Trustworthy Machine Learning

Machine learning has made great advances over the past year and many techniques have found their ways into applications. This leads to an increasing demand of techniques that not only perform well - but are also "trustworthy".

Trustworthiness includes:
- Interpretability of the prediction
- Robustness against changes to the input, which occur naturally or with malicious intend
- Privacy preserving machine learning (e.g. when dealing with sensitive data such as in health applications)
- Fairness
- ...

Description

As a proseminar’s primary purpose is to learn presentation skills, the seminar will feature two presentations from each student. 

In the first half of the semester, we will have presentations of two topics each week. After each presentation, fellow students and lecturers will provide feedback on how to improve the presentation. This general feedback must then be taken into account for the second half of the semester, where again each student will present.

Grading

The first presentations  will count towards 30% of the overall grade, the second presentation will count towards 70% of the overall grade. Attendance in the proseminar meetings is mandatory. At most one session can be skipped, after that you need to bring a doctor’s note to excuse your absence.

Winter 2021/22

Machine Learning in Cyber Security

Recent advances in Machine Learning has lead to near (or beyond) human-level performance in many tasks - autonomous driving, voice assistance, playing a variety of games. In terms of privacy and security, this is a double-edged sword. ML techniques can be used to efficiently detect and prevent attacks (e.g., intrusion detection). However, their deployment to many real-world sensitive systems (e.g., self-driving cars, the cloud) also makes them susceptible to numerous attacks, such as introducing imperceptible perturbations in inputs and forcing ML systems behave in unintended ways.

The course explores in-depth both of these sides to Machine Learning and Cyber Security. The content addresses the following areas:

  1. ML overview
  2. ML for improving security
  3. Attacks on ML
  4. Defenses for ML
  5. ML and Privacy

While we do a brief recap in the beginning, the course requires knowledge on Machine Learning.

Date for lecture: Tuesdays noon to 2pm. 

Date for exercise: Fridays 2pm to 4pm

Due to the size of the course - the lecture will start in an online format until further notice.

The course requires prior knowledge on Machine Learning.

Once you have registered - please find internal information and schedule and links here (under construction).

Summer 2020

Proseminar: Trustworthy Machine Learning

Machine learning has made great advances over the past year and many techniques have found their ways into applications. This leads to an increasing demand of techniques that not only perform well - but are also "trustworthy".

Summer 2020

Lecture: High Level Computer Vision

This course will cover essential techniques for high-level computer vision. These techniques facilitate semantic interpretation of visual data, as it is required for a broad range of applications like robotics, driver assistance, multi-media retrieval, surveillance etc.

Winter 2019/20

Lecture: Machine Learning in Cybersecurity

Recent advances in Machine Learning has lead to near (or beyond) human-level performance in many tasks - autonomous driving, voice assistance, playing a variety of games.

More information