Send email Copy Email Address
Research Group

Schönherr

Our research includes all kinds of attacks against real-world machine learning systems with a focus on input data like audio, speech, and text. In our research we focus on security and privacy threats equally and aim to use domain knowledge to develop adaptive detection mechanisms and countermeasures, e.g. for Deepfakes and adversarial examples.

Head of Group

Lea Schönherr

Email

Phone

Address

Stuhlsatzenhaus 5
66123 Saarbrücken (Germany)

Members

Placeholder

David Pape

Soumya Shaw
Placeholder

Jonathan Evertz
Placeholder

Yage Zhang

Most Recent Publications

Year 2024

2024-10-09

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2024-10-09

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Threat Detection and Defenses
Authors
  • Edoardo Debenedetti
  • Javier Rando
  • Daniel Paleka
  • Silaghi Fineas Florin
  • Dragos Albastroiu
  • Niv Cohen
  • Yuval Lemberg
  • Reshmi Ghosh
  • Rui Wen
  • Ahmed Salem
  • Giovanni Cherubin
  • Santiago Zanella-Beguelin
  • Robin Schmid
  • Victor Klem
  • Takahiro Miki
  • Chenhao Li
  • Stefan Kraft
  • Mario Fritz
  • Florian Tramèr
  • Sahar Abdelnabi
  • Lea Schönherr
Visit Detail Page
2024-08-14

The Imitation Game: Exploring Brand Impersonation Attacks on Social Media Platforms

Conference / Medium

Usenix Security Symposium (USENIX-Security)

Tags
Threat Detection and Defenses
Authors
Full Paper Visit Detail Page
2024-07-03

BUILD: Buffer-free Incremental Learning with OOD Detection for the Wild

Conference / Medium

International Conference on Machine Learning (ICML)

Tags
Threat Detection and Defenses
Authors
Full Paper Visit Detail Page
2024-06-28

Generated Audio Detectors are Not Robust in Real-World Conditions

Conference / Medium

International Conference on Machine Learning (ICML)

Tags
Threat Detection and Defenses
Authors
Full Paper Visit Detail Page