RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation

본문 미리보기

arXiv:2607.27373v1 Announce Type: new Abstract: Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing prompt-based policy evasion remains challenging, and adversaries continue to "jailbreak" LLMs by crafting prompts that circumvent implemented safety mechanisms. Prior work has established cipher-mediated interaction, code-embedd