# ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs

arXiv: https://arxiv.org/abs/2502.13162 · HTML: https://mlsanity.com/paper/2502.13162/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- First posted on arXiv 16 Feb 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Built on by (most cited first, 7 of 7)

- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines](https://mlsanity.com/paper/2601.09465/) (2026)
- [Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding](https://mlsanity.com/paper/2508.17971/) (2025)
- [Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening](https://mlsanity.com/paper/2602.05386/) (2026)
- [DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection](https://mlsanity.com/paper/2604.12548/) (2026)
- [Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production](https://mlsanity.com/paper/2608.08471/) (2026)
- [Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning](https://mlsanity.com/paper/2609.10142/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face limitations in adaptability, interpretability, and customization, constraining their effectiveness against evolving threats. To address these challenges, we propose ShieldLearner, a novel paradigm that mimics human learning in defense. Through trial and error, it autonomously distills attack signatures into a Pattern Atlas and synthesizes defense heuristics into a Meta-analysis Framework, enabling systematic and interpretable threat detection. Furthermore, we introduce Adaptive Adversarial Augmentation to generate adversarial variations of successfully defended prompts, enabling continuous self-improvement without model retraining. In addition to standard benchmarks, we create a hard test set by curating adversarial prompts from the Wildjailbreak dataset, emphasizing more concealed malicious intent. Experimental results show that ShieldLearner achieves a significantly higher defense success rate than existing baselines on both conventional and hard test sets, while also operating with lower computational overhead, making it a practical and efficient solution for real-world adversarial defense.