Scholar
Lea Schönherr
Google Scholar ID: DtLfiGoAAAAJ
CISPA Helmholtz Center for Information Security
Trustworthy ML
Trustworthy Generative AI
Computer Security
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,126
H-index
16
i10-index
17
Publications
20
Co-authors
67
list available
Contact
Email
lea.schoenherr@gmail.com
Twitter
Open ↗
GitHub
Open ↗
Publications
7 items
Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
2026
Cited
0
Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection
2026
Cited
0
Chasing Shadows: Pitfalls in LLM Security Research
2025
Cited
0
Are Modern Speech Enhancement Systems Vulnerable to Adversarial Attacks?
2025
Cited
0
Fake It Until You Break It: On the Adversarial Robustness of AI-generated Image Detectors
arXiv.org · 2024
Cited
3
Prompt Obfuscation for Large Language Models
arXiv.org · 2024
Cited
1
Whispers in the Machine: Confidentiality in LLM-integrated Systems
arXiv.org · 2024
Cited
23
Resume (English only)
Academic Achievements
Published multiple papers at NeurIPS, USENIX Security, IEEE S&P, ICML Workshops, and ArXiv
Notable works include: 'Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition' (NeurIPS 2024)
'The Imitation Game: Exploring Brand Impersonation Attacks on Social Media Platforms' (USENIX Security)
'A Representative Study on Human Detection of Artificially Generated Media Across Countries' (IEEE S&P)
'CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models' (IEEE SatML)
'Generated Audio Detectors are Not Robust in Real-World Conditions' (ICML Workshop)
'Prompt Obfuscation for Large Language Models' (ArXiv)
'Fake It Until You Break It: On the Adversarial Robustness of AI-generated Image Detectors' (ArXiv)
'HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data' (ArXiv)
Co-authors
67 total
Thorsten Holz
Max Planck Institute for Security and Privacy (MPI-SP)
Thorsten Eisenhofer
Technische Universität Berlin
Dorothea Kolossa
Technische Universität Berlin
Asja Fischer
Professor for Machine Learning, Ruhr University Bochum
Co-author 5
Mario Fritz
Faculty CISPA Helmholtz Center for Information Security; Professor Saarland University
Sahar Abdelnabi
AI Security Researcher, Microsoft
Antonio Emanuele Cinà
Assistant Professor @ University of Genoa
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up