ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming

Mario Rodríguez Béjar, Francisco J. Cortés-Delgado, S. Braghin, Jose L. Hernández-Ramos

Abstract

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies, constitutes a powerful attack surface, with hand-crafted multi-turn scaffolds consistently outperforming single-turn manipulations on capable models. However, automated optimization-based red-teaming has remained largely limited to the single-turn setting, iterating ove

Categories

Cite This Resource

@article{llmsec202600127,
  title = {ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming},
  author = {Mario Rodríguez Béjar and Francisco J. Cortés-Delgado and S. Braghin and Jose L. Hernández-Ramos},
  year = {2026},
  url = {https://arxiv.org/abs/2605.02647},
}