Beurer-Kellner, Luca

Prompting Is Programming: A Query Language for Large Language Models

Beurer-Kellner, L., Fischer, M., & Vechev, M. (2023) · Proceedings of the ACM on Programming Languages

Topic ModelingNatural Language Processing Techniques

Cited by 117

Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation

Beurer-Kellner, L., Fischer, M., & Vechev, M. (2024) · arXiv

Natural Language Processing TechniquesTopic Modeling

Cited by 5

Design Patterns for Securing LLM Agents against Prompt Injections

Beurer-Kellner, L., Buesser, B., Creţu, A.-M., Debenedetti, E., Dobos, D., Fabian, D., Fischer, M., Froelicher, D., Grosse, K., Naeff, D., et al. (2025) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 2

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

Schmotz, D., Beurer-Kellner, L., Abdelnabi, S., & Andriushchenko, M. (2026) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 0

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

Das, D., Piet, J., Kaviani, D., Beurer-Kellner, L., Tramèr, F., & Wagner, D. (2026) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 0

Stealing Reasoning Traces from Proprietary LLM APIs

Panfilov, A., Schmotz, D., Shumailov, I., Beurer-Kellner, L., Schaeffer, J., Prabhu, A., Geiping, J., & Andriushchenko, M. (2026) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 0