mlsanityData to 14 Oct 2026

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs

arXiv 2502.19041 ↗First posted 26 Feb 2025cs.CRcited by 9

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Although Aligned Large Language Models (LLMs) are trained to refuse harmful requests, they remain vulnerable to jailbreak attacks. Unfortunately, existing methods often focus on surface-level patterns, overlooking the deeper attack essences. As a result, defenses fail when attack prompts change, even though the underlying "attack essence" remains the same. To address this issue, we introduce EDDF, an Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs. EDDF is a plug-and-play input-filtering method and operates in two stages: 1) offline essence database construction, and 2) online adversarial query detection. The key idea behind EDDF is to extract the "attack essence" from a diverse set of known attack instances and store it in an offline vector database. Experimental results demonstrate that EDDF significantly outperforms existing methods by reducing the Attack Success Rate by at least 20%, underscoring its superior robustness against jailbreak attacks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 28 of its 46 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

28 of 46 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation1 Feb
  2. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey5 Jul
  3. 2024WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models26 Jun
  4. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks3 Apr
  5. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks2 Mar
  6. 2024Defending Jailbreak Prompts via In-Context Adversarial Game20 Feb
  7. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily14 Nov
  8. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  9. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  10. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  11. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  12. 2023Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM18 Sep
3 more
  1. 2023Detecting Language Model Attacks with Perplexity27 Aug
  2. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  3. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 13

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  5. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  6. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  7. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  8. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  9. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  10. 2023The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensivenesscited by 67
  11. 2025On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspectivecited by 41
  12. 2024Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!cited by 37
1 more
  1. 2024MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?cited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 2.

9 papers.

  1. 2025SoK: Evaluating Jailbreak Guardrails for Large Language Modelscited by 21
  2. 2025Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMscited by 8
  3. 2025TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluationscited by 7
  4. 2026FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environmentscited by 7
  5. 2025ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast & Slow Reasoning for Robust Agent Defensecited by 5
  6. 2025Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attackscited by 5
  7. 2025Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignmentcited by 3
  8. 2025Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Modelscited by 1
  9. 2026Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screeningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
  2. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
  3. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
  4. 2025Proactive defense against LLM Jailbreak
  5. 2025CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
  6. 2025Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
  7. 2024Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
  8. 2024HSF: Defending against Jailbreak Attacks with Hidden State Filtering