Johan Wahréus

According to our database¹, Johan Wahréus authored at least 3 papers between 2024 and 2025.

Collaborative distances:

Timeline

Book In proceedings Article PhD thesis Dataset Other

2025

Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing.

[DOI]

CoRR, March, 2025

CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models.

[DOI]

CoRR, January, 2025

2024

Jailbreaking Large Language Models Through Content Concretization.

[DOI]

Proceedings of the Game Theory and AI for Security, 2024