mlsanityData to 14 Oct 2026

Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations

arXiv 2511.18933 ↗First posted 24 Nov 2025cs.CR cs.AIcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level, model-level, and training-time interventions, followed by three proposed defense strategies. First, a Prompt-Level Defense Framework detects and neutralizes adversarial inputs through sanitization, paraphrasing, and adaptive system guarding. Second, a Logit-Based Steering Defense reinforces refusal behavior through inference-time vector steering in safety-sensitive layers. Third, a Domain-Specific Agent Defense employs the MetaGPT framework to enforce structured, role-based collaboration and domain adherence. Experiments on benchmark datasets show substantial reductions in attack success rate, achieving full mitigation under the agent-based defense. Overall, this study highlights how jailbreaks pose a significant security threat to LLMs and identifies key intervention points for prevention, while noting that defense strategies often involve trade-offs between safety, performance, and scalability. Code is available at: https://github.com/Kuro0911/CS5446-Project

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 22 of its 30 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

22 of 30 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection14 Oct
  2. 2024GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis21 Feb
  3. 2024SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding14 Feb
  4. 2024JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs8 Feb
  5. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug

Other references · 17

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2017Deep reinforcement learning from human preferencescited by 3,912
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  5. 2018Datasheets for Datasetscited by 1,386
  6. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 505
  7. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 223
  8. 2024Safety Layers in Aligned Large Language Models: The Key to LLM Securitycited by 134
  9. 2024MaxMin-RLHF: Alignment with Diverse Human Preferencescited by 123
  10. 2024Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimizationcited by 118
  11. 2024Reinforcement Learning for LLM Post-Training: A Surveycited by 92
  12. 2024On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularizationcited by 72
5 more
  1. 2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAIcited by 35
  2. 2025HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden Statescited by 33
  3. 2025One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMscited by 29
  4. 2025A Survey of Attacks on Large Language Modelscited by 15
  5. 2025Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Qualitycited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
  2. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey
  3. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
  4. 2025SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
  5. 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
  6. 2025AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
  7. 2025Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
  8. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval