News
Oral Exam GradesWritten on 18.08.23 (last change on 18.08.23) by Hai Huang Dear all, The grades for this course are now available on LSF. Please have a look. Best, |
The Final Oral Exam ScheduleWritten on 18.07.23 (last change on 18.07.23) by Hai Huang Dear all, The final oral exam will take place from July 25th to August 4th at Office 3.17 of the CISPA building. For each student who has passed the project test, please book a time slot for the oral exam on Doodle. Each time slot has 30 minutes. Good luck! Best, |
List of Students That Are Admitted to the Oral ExamWritten on 04.07.23 (last change on 04.07.23) by Yugeng Liu Dear all, A list of students that are admitted to the exam is now available here. If you have any questions, please contact our TAs. Best, Yugeng |
Course EvaluationWritten on 21.06.23 by Yang Zhang Dear all, I would like to ask you to review the course with the following link. https://qualis.uni-saarland.de/eva/?l=143568&p=kimn52 Best, Yang |
Forum OpeningWritten on 05.06.23 (last change on 12.06.23) by Hai Huang Dear all, The forum for this course has been available. You can post messages on it to find potential group members for the semester project. Best, |
Updates on the Semester ProjectWritten on 05.06.23 by Hai Huang Hi everyone, The Jupyter notebook example and the instructions for the semester project have been uploaded to the CMS (Information -> Materials -> Project). Please include the necessary information of your group (i.e., names and student IDs) in your submission email. You can submit your… Read more Hi everyone, The Jupyter notebook example and the instructions for the semester project have been uploaded to the CMS (Information -> Materials -> Project). Please include the necessary information of your group (i.e., names and student IDs) in your submission email. You can submit your results multiple times before the deadline. After you submit your prediction results to us, we will send you back the evaluation results in three days. Please do NOT share your results with anyone outside of your group. Best, |
Semester Project Documents UploadedWritten on 31.05.23 (last change on 31.05.23) by Hai Huang Hi all, The documents for the semester project have been uploaded to https://drive.google.com/drive/folders/1LZhRnyw9aJ2NzKpIRqJdZACAQpN5ulTY?usp=sharing. Please download all data files and refer to README.md for more details. You can team up to complete the project with up to four people… Read more Hi all, The documents for the semester project have been uploaded to https://drive.google.com/drive/folders/1LZhRnyw9aJ2NzKpIRqJdZACAQpN5ulTY?usp=sharing. Please download all data files and refer to README.md for more details. You can team up to complete the project with up to four people in each group. You are required to submit four prediction result files for this project to hai.huang@cispa.de or yugeng.liu@cispa.de. The real test accuracy will then be evaluated by us. The mean of all four test accuracy should be higher than 80% such that all of your group members will be eligible to take the final oral exam. The deadline is July 3rd. We will introduce this project in the next lecture on June 5th. Thanks! Best, Hai |
Re-scheduled Lecture Time on May 8thWritten on 08.05.23 by Hai Huang Hello everyone, Today's lecture will start at 2:30 pm, thanks! Best, Hai |
kick-off and chapter slides uploadedWritten on 24.04.23 by Yang Zhang Dear all, The slides are uploaded to cms. You could find them under information->material. Best, Yang |
first lecture timeWritten on 12.04.23 by Yang Zhang Hi everyone, The first lecture will happen on April 24th; the location will be CISPA's lecture hall. Best, Yang |
Attacks Against Machine Learning Models
Overview
This course will cover the topic of attacks against machine learning models
- Privacy
- Membership inference
- Dataset reconstruction
- Attribute inference
- Security
- Backdoor
- Model stealing
- Safety
- Hijacking
- Toxicity
Prerequisites
- Basic knowledge of machine learning and data mining
- Security background is not needed
Logistics
Location: Lecture hall, CISPA Building, E9 1
Lecturer: Yang Zhang
Assistants: Yugeng Liu, Boyang Zhang, Xinyue Shen, Hai Huang, Wai Man Si
Contact: boyang.zhang@cispa.de
Time: Monday 14:00 - 15:30
Contact: Boyang Zhang (boyang.zhang@cispa.de)
Schedule
- 4.24 Membership 1
- 5.8 Membership 2
- 5.15 Attribute Inference
- 5.22 Data Reconstruction 1
- 6.5 Data Reconstruction 2 + Model Stealing (Rui Wen)
- 6.12 Adversarial Example 1 (Zhengyu Zhao)
- 6.19 Poisoning (Zhengyu Zhao)
- 6.26 Backdoor (Yugeng Liu)
- 7.3 GNN Attacks (Xinlei He)
- 7.10 Self-supervised Learning Attacks (Xinlei He)
- 7.17 Fun (and Funny) Attacks (Edward Boyang Zhang and Vera Xinyue Shen)
Grading
The course will be graded by 100% oral exam.
Note that students who have taken the advanced lectures
- Machine Learning Privacy
- Privacy Enhancing Technologies (2018-2021)
cannot take this one due to the significant overlap between them.