Torsten Krauß

CoRR, 2024

ClearStamp: A Human-Visible and Robust Model-Ownership Proof based on Transposed Model Training.

[BibT_eX]

[DOI]

Proceedings of the 33rd USENIX Security Symposium, 2024

Verify your Labels! Trustworthy Predictions and Datasets via Confidence Scores.

[BibT_eX]

[DOI]

Proceedings of the 33rd USENIX Security Symposium, 2024

CrowdGuard: Federated Backdoor Detection in Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

Automatic Adversarial Adaption for Stealthy Poisoning Attacks in Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

Cloud-Based Machine Learning Models as Covert Communication Channels.

[BibT_eX]

[DOI]

Proceedings of the 19th ACM Asia Conference on Computer and Communications Security, 2024

2023

ClearMark: Intuitive and Robust Model Watermarking via Transposed Model Training.

[BibT_eX]

[DOI]

CoRR, 2023

Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations.

[BibT_eX]

[DOI]

CoRR, 2023

Security of NVMe Offloaded Data in Large-Scale Machine Learning.

[BibT_eX]

[DOI]

Raphael Götz

Proceedings of the Computer Security - ESORICS 2023, 2023

MESAS: Poisoning Defense for Federated Learning Resilient against Adaptive Attackers.

[BibT_eX]

[DOI]