Faculty
Dr. Lea Schönherr ist Tenure-Track-Faculty am CISPA Helmholtz-Zentrum für Informationssicherheit. Sie forscht zu Informationssicherheit mit einem Schwerpunkt auf Adversarial Machine Learning. Sie promovierte 2021 an der Ruhr-Universität Bochum, wo sie von Professor Dr.-Ing. Dorothea Kolossa in der Arbeitsgruppe Kognitive Signalverarbeitung betreut wurde. Sie erhielt zwei Stipendien von UbiCrypt (DFG-Graduiertenkolleg) und CASA (DFG-Exzellenzcluster).
Usenix Security Symposium (USENIX-Security)
Prompt Obfuscation for Large Language Models
GI International Conference on Detection of Intrusions and Malware and Vulnerability Assessment (DIMVA)
Exploring the Potential of LLMs for Code Deobfuscation
International Conference on Learning Representations (ICLR)
σ -zero: Gradient-based Optimization of ℓ0-norm Adversarial Examples
Conference on Neural Information Processing Systems (NeurIPS)
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
Conference on Neural Information Processing Systems (NeurIPS)
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Usenix Security Symposium (USENIX-Security)
The Imitation Game: Exploring Brand Impersonation Attacks on Social Media Platforms
International Conference on Machine Learning (ICML)
BUILD: Buffer-free Incremental Learning with OOD Detection for the Wild
International Conference on Machine Learning (ICML)
Generated Audio Detectors are Not Robust in Real-World Conditions
IEEE Symposium on Security and Privacy (S&P)
A Representative Study on Human Detection of Artificially Generated Media Across Countries
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models