mlsanityData to 7 Oct 2026

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs

arXiv 2511.07480 ↗First posted 9 Nov 2025cs.CR cs.AIcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

With the widespread application of large language models (LLMs) in various fields, the security challenges they face have become increasingly prominent, especially the issue of jailbreak. These attacks induce the model to generate erroneous or uncontrolled outputs through crafted inputs, threatening the generality and security of the model. Although existing defense methods have shown some effectiveness, they often struggle to strike a balance between model generality and security. Excessive defense may limit the normal use of the model, while insufficient defense may lead to security vulnerabilities. In response to this problem, we propose a Knowledge Graph Defense Framework (KG-DF). Specifically, because of its structured knowledge representation and semantic association capabilities, Knowledge Graph(KG) can be searched by associating input content with safe knowledge in the knowledge base, thus identifying potentially harmful intentions and providing safe reasoning paths. However, traditional KG methods encounter significant challenges in keyword extraction, particularly when confronted with diverse and evolving attack strategies. To address this issue, we introduce an extensible semantic parsing module, whose core task is to transform the input query into a set of structured and secure concept representations, thereby enhancing the relevance of the matching process. Experimental results show that our framework enhances defense performance against various jailbreak attack methods, while also improving the response quality of the LLM in general QA scenarios by incorporating domain-general knowledge.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 24 of its 36 references that are in the map. First posted on arXiv 9 Nov 2025.

Builds on

24 of 36 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks3 Apr
  2. 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuning9 Feb
  3. 2024Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks30 Jan
  4. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  5. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily14 Nov
  6. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  7. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  8. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  9. 2023Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM18 Sep
  10. 2023Detecting Language Model Attacks with Perplexity27 Aug
  11. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  12. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
1 more
  1. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 11

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2020Learning to summarize from human feedbackcited by 2,562
  4. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  5. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 268
  6. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 197
  7. 2023Planning with Large Language Models for Code Generationcited by 179
  8. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 124
  9. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  10. 2024A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systemscited by 74
  11. 2023Improving Large Language Model Fine-tuning for Solving Math Problemscited by 48

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
  2. 2025A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Models
  3. 2026AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
  4. 2025Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
  5. 2025QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
  6. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
  7. 2025CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
  8. 2025JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation