David Pape

I am a PhD student at CISPA Helmholtz Center for Information Security, advised by Dr. Lea Schönherr.

My research focuses on the security and trustworthiness of large language models and AI agents. I am particularly interested in adversarial robustness, security evaluation, and reproducibility.

Before joining CISPA, I obtained my Master's degree in IT Security from Ruhr University Bochum, where I focused on machine learning security.

David Pape

Publications

2026

Chasing Shadows: Pitfalls in LLM Security Research

Jonathan Evertz, Niklas Risse, Nicolai Neuer, Andreas Müller, Philipp Normann, Gaetano Sapia, Srishti Gupta, David Pape, Soumya Shaw, Devansh Srivastav, Christian Wressnegger, Erwin Quiring, Thorsten Eisenhofer, Daniel Arp, and Lea Schönherr

NDSS 2026Paper

2025

2023

Preprints

Invited Talks

Protecting, Executing, and Auditing: Security Challenges Across the LLM Lifecycle

AI Security Afternoon, organized by AI Safety Saarland · Saarbrücken, Germany

Event page

Teaching & supervision

Trustworthy Machine Learning

Teaching Assistant · University of Hamburg

Trustworthy Generative Machine Learning (Seminar)

Teaching Assistant · Saarland University

Security courses

Teaching Assistant · Ruhr-Universität Bochum

Chairs of Systems Security, Embedded Security, and Cryptology & IT Security

Thesis supervision

Saarland University · One bachelor’s thesis and one master’s thesis

Reviewing

Conferences

CYBERSEC 2026 · ICML 2026 (Gold Reviewer) · NeurIPS 2026 · AAAI 2027

Workshops

AISec (ACM CCS 2024, 2025, 2026; Top Reviewer, 2025) · DeMeSSAI (IEEE EuroS&P 2025, 2026) · FLMSec (NeurIPS 2026)

Artifact evaluation

USENIX Security 2026