CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection

Abstract

Jailbreak attacks pose a serious challenge to the safe deployment of large language models (LLMs). We introduce CCFC (Core&Core-Full-Core), a dual-track, prompt-level defense framework designed to mitigate LLMs'vulnerabilities from prompt injection and structure-aware jailbreak attacks. CCFC operates by first isolating the semantic core of a user query via few-shot prompting, and then evaluating the query using two complementary tracks: a core-only track to ignore adversarial distractions (e.g.,

Categories

Framework mappings

Suggested from the entry's categories.

@misc{hu2025ccfc,
  title = {{CCFC: Core \& Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection}},
  author = {Jiaming Hu and Haoyu Wang and Debarghya Mukherjee and I. Paschalidis},
  year = {2025},
  month = aug,
  eprint = {2508.14128},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2508.14128},
  url = {https://www.semanticscholar.org/paper/3fe877de5fe0afa33a3ff9ff0ea0daf53b842be1}
}