News
final results are outWritten on 10.02.23 by Yang Zhang Dear all, The final results of the seminar are available on LSF. Best, Yang |
Seminar evaluationWritten on 31.01.23 by Yang Zhang Dear all, The evaluation for the seminar started. Please use the link below. https://qualis.uni-saarland.de/eva/?l=1854&p=61k08y Please do so before February 10th, after that, we can put your scores in LSF. I'm sorry for the delay but I only got the evaluation link today from… Read more Dear all, The evaluation for the seminar started. Please use the link below. https://qualis.uni-saarland.de/eva/?l=1854&p=61k08y Please do so before February 10th, after that, we can put your scores in LSF. I'm sorry for the delay but I only got the evaluation link today from Qualis-team. Again, I wish everyone good luck for the exams. Best, Yang |
Schedule of presentationWritten on 09.11.22 by Xinyue Shen Dear all, After receiving your responses, we have arranged a schedule for you to give the presentations (see it at the end of this message). See you next week. :) Best, Dear all, After receiving your responses, we have arranged a schedule for you to give the presentations (see it at the end of this message). See you next week. :) Best, ----------------------------------------------------------------- 21.11: 28.11: 05.12: 12.12: |
paper assignmentWritten on 07.11.22 by Yang Zhang Dear all, Please send your paper preferences (3 papers ranked from high to low) to xinyue.shen@cispa.de by the end of tomorrow. If you plan to present next Monday, please also indicate it in your email. The assignment will be ready by 1pm Wednesday! Best, Yang |
Privacy of Machine Learning
Machine learning has witnessed tremendous progress during the past decade, and data is the key to such success. However, in many cases, machine learning models are trained on sensitive data, e.g., biomedical records, and such data can be leaked from trained machine learning models. In this seminar, we will cover the newest research papers in this direction.
Logistics:
Time: Monday 2pm-4pm
Location: Zoom
TAs:
- Xinyue Shen (xinyue.shen@cispa.de)
- Boyang Zhang (boyang.zhang@cispa.de)
- Zeyang Sha (zeyang.sha@cispa.de)
List of Papers:
- Membership Leakage in Label-Only Exposures
- GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
- Membership Inference Attacks by Exploiting Loss Trajectory
- Dataset Inference: Ownership Resolution in Machine Learning
- Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
- Extracting Training Data from Large Language Models
- Reconstructing Training Data with Informed Adversaries
- You are who you know and how you behave: Attribute inference attacks via users' social friends and behaviors
- Overlearning Reveals Sensitive Attributes
- ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
- Quantifying and Mitigating Privacy Risks of Contrastive Learning
- Model Stealing Attacks Against Inductive Graph Neural Networks
- Stealing Links from Graph Neural Networks
- Stealing Hyperparameters in Machine Learning
- Stealing Machine Learning Models via Prediction APIs
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
- The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks.
- Exploiting Explanations for Model Inversion Attacks
- Deep Learning with Differential Privacy
- Auditing Data Provenance in Text-Generation Models
- UnGANable: Defending Against GAN-based Face Manipulation
- SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders