lea

 

Lea Schönherr

Faculty


I am a tenure track faculty at CISPA Helmholtz Center for Information Security interested in information security with a focus on adversarial machine learning . Before that I was working at Ruhr University Bochum (RUB), Germany, in the DFG Cluster of Excellence “Cyber Security in the Age of Large-Scale Adversaries“ (CASA).

 

My research includes all kinds of attacks against machine learning models, including adversarial examples and poisoning attacks with a focus on signal-driven input data like audio and speech by utilizing approaches based on signal processing. I aim to develop domain-adaptive detection mechanisms and countermeasures, e.g., for Deepfakes and adversarial examples.

 

During my Ph.D., I focused on the robustness of neural networks and the security of speech-based systems. I received my Ph.D. in 2021 from Ruhr University Bochum, where I was advised by Prof. Dr.-Ing. Dorothea Kolossa at the Cognitive Signal Processing group at Ruhr University Bochum (RUB), Germany. I received two scholarships from UbiCrypt (DFG Research Training Group) and CASA (DFG Cluster of Excellence).

 

I obtained my Master's degree in Electrical Engineering and Information Technology at RUB in 2015 after graduating from the University of Applied Science in Mannheim in Biomedical Engineering.

  ·  

 

2022

Timm Koppelmann, Luca Becker, Alexandru Nelus, Rene Glitza, Lea Schönherr, Rainer Martin

Clustering-based Wake Word Detection in Privacy-aware Acoustic Sensor Networks

INTERSPEECH 2022    [Paper] [BibTex]

Lea Schönherr, Maximilian Golla, Thorsten Eisenhofer, Jan Wiele, Dorothea Kolossa, and Thorsten Holz

Unacceptable, where is my Privacy? Exploring Accidental Triggers of Smart Speakers

Computer Speech & Language    [Paper] [Website] [BibTex]

2021

Joel Frank and Lea Schönherr

WaveFake: A Data Set to Facilitate Audio DeepFake Detection

NeurIPS Datasets and Benchmarks Track 2021    [Paper][Code] [Talk] [BibTex]

Thorsten Eisenhofer, Lea Schönherr, Joel Frank, Lars Speckemeier, Dorothea Kolossa, and Thorsten Holz

Dompteur: Taming Audio Adversarial Examples

USENIX Security 2021    [Paper] [Code] [Talk] [BibTex]

Lea Schönherr

Adverarially Robust Speech and Speaker Recognition

Ruhr University Bochum   [Dissertation] [BibTex]

Timm Koppelmann, Alexandru Nelus, Lea Schönherr, Dorothea Kolossa, and Rainer Martin

Privacy-Preserving Feature Extraction for Cloud-Based Wake Word Verification

INTERSPEECH 2021    [Paper] [BibTex]

Hojjat Aghakhani, Thorsten Eisenhofer, Lea Schönherr, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, and Giovanni Vigna

VENOMAVE: Clean-Label Poisoning Against Speech Recognition

arXiv 2021    [Paper] [BibTex]

2020

Joel Frank, Thorsten Eisenhofer, Lea Schönherr, Asja Fischer, Dorothea Kolossa, and Thorsten Holz

Leveraging Frequency Analysis for Deep Fake Image Recognition

ICML 2020    [Paper] [Code] [Talk] [BibTex]

Lea Schönherr, Thorsten Eisenhofer, Steffen Zeiler, Thorsten Holz, and Dorothea Kolossa

Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems

ACSAC 2020    [Paper] [Talk] [BibTex]

Sina Däubener, Lea Schönherr, Asja Fischer, and Dorothea Kolossa

Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification

INTERSPEECH 2020    [Paper] [Code] [BibTex]

Jan Freiwald, Lea Schönherr, Christopher Schymura, Steffen Zeiler, and Dorothea Kolossa

Loss Functions for Deep Monaural Speech Enhancement

IJCNN 2020    [Paper] [BibTex]

2019

Lea Schönherr, Katharina Kohls, Steffen Zeiler, Thorsten Holz, and Dorothea Kolossa

Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding

NDSS 2019    [Paper] [Website] [Code] [Talk] [BibTex]

2017

Lea Schönherr, Steffen Zeiler, and Dorothea Kolossa

Spoofing Detection via Simultaneous Verification of Audio-Visual Synchronicity and Transcription

ASRU 2017    [Paper] [BibTex]

2016

Lea Schönherr, Dennis Orth, Martin Heckmann, and Dorothea Kolossa

Environmentally Robust Audio-Visual Speaker Identification

SLT 2016    [Paper] [BibTex]