📄 Paper

MAGIC:

Authors: Xiaoyu Wen, Zhida He, Han Qi, Ziyu Wan, Ying Wen, Tianhang Zheng, Xingcheng Xu, Chaochao Lu, Qiaosheng Zhang.
Paper: https://arxiv.org/pdf/2602.01539
Code & Models: https://huggingface.co/XiaoyuWen/MAGIC-Qwen2.5-14B-Instruct

This repository provides the official implementation and model checkpoints described in the paper.

🧠 MAGIC Framework Overview

MAGIC is a co-evolving attacker–defender adversarial game framework designed to improve the robustness and safety of large language models.

Instead of relying on static red-teaming or fixed safety datasets, MAGIC formulates LLM safety alignment as a dynamic game between:

an attacker, which continuously generates increasingly sophisticated harmful or policy-violating prompts, and
a defender, which adapts through iterative training to resist these attacks while preserving helpfulness.

Through this co-evolutionary process, both sides improve over time, enabling the defender model to generalize to unseen and adaptive attacks.

This model, MAGIC-Qwen2.5-14B-Instruct, is the defender model trained under the MAGIC framework based on Qwen2.5-14B-Instruct, demonstrating significantly improved robustness against jailbreak and attack prompts.

🤗 Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "XiaoyuWen/MAGIC-Qwen2.5-14B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

prompt = "Explain why jailbreaking LLMs is dangerous."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=8192)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📚 Citation

If you find this work useful, please cite:

@article{wen2026magic,
    title={MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety},
    author={Wen, Xiaoyu and He, Zhida and Qi, Han and Wan, Ziyu and Wen, Ying and Zheng, Tianhang and Xu, Xingcheng and Lu, Chaochao and Zhang, Qiaosheng},
    journal={arXiv preprint arxiv:2602.01539},
    year={2026}
}