APA-Zitierstil (7. Ausg.)

Li, X., Ning, Y., Bao, Z., Xu, M., Chen, J., & Qian, T. (2025). CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations.

Chicago-Zitierstil (17. Ausg.)

Li, Xiaohu, Yunfeng Ning, Zepeng Bao, Mayi Xu, Jianhao Chen, und Tieyun Qian. CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on Their Internal Representations. 2025.

MLA-Zitierstil (9. Ausg.)

Li, Xiaohu, et al. CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on Their Internal Representations. 2025.