摘要: Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection(WWW 2025) 通过大型语言模型进行对抗风格增强以实现鲁棒的假新闻检测 作者:Sungwon Park, Sungwon 阅读全文
posted @ 2025-12-31 21:02 卓然666 阅读(2) 评论(0) 推荐(0)
摘要: Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models (EMNLP 2025) 使用语言模型生成的对抗样本攻击虚假信息检测 作者:Piotr Przybyła, Euan 阅读全文
posted @ 2025-12-31 20:45 卓然666 阅读(3) 评论(0) 推荐(0)