mlsanityData to 14 Oct 2026

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

arXiv 2508.14128 ↗First posted 19 Aug 2025cs.CR cs.AIcited by 3

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

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., toxic suffixes or prefix injections), and a core-full-core (CFC) track to disrupt the structural patterns exploited by gradient-based or edit-based attacks. The final response is selected based on a safety consistency check across both tracks, ensuring robustness without compromising on response quality. We demonstrate that CCFC cuts attack success rates by 50-75% versus state-of-the-art defenses against strong adversaries (e.g., DeepInception, GCG), without sacrificing fidelity on benign queries. Our method consistently outperforms state-of-the-art prompt-level defenses, offering a practical and effective solution for safer LLM deployment.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 26 of its 32 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

26 of 32 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation1 Feb
  2. 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes1 Mar
  3. 2024GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis21 Feb
  4. 2024SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding14 Feb
  5. 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks30 Jan
  6. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  7. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  8. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  9. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  10. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  11. 2023Certifying LLM Safety against Adversarial Prompting6 Sep
  12. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
1 more
  1. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2022Training language models to follow instructions with human feedbackcited by 15,971
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  9. 2021Ethical and social risks of harm from Language Modelscited by 966
  10. 2024A Survey on Large Language Models for Code Generationcited by 658
  11. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  12. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
1 more
  1. 2020Adversarial Training for Large Neural Language Modelscited by 111

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Modelscited by 2
  2. 2026Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Frameworkcited by 0
  3. 2026Distributionally Robust Token Optimization in RLHFcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
  2. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
  3. 2024Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
  4. 2026MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
  5. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey
  6. 2025DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification
  7. 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
  8. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing