arXiv cs.CL· Dexin Liu, Fan Yang, Zimu Wang, Xunfei Zhu, Bolin Ren, Bingyan Zhang, Wei Wang, Qi Chen·· 12 小时前AI 评分27
MANTIS：面向假新闻检测的多轴新闻变换实例级压力测试与最坏情况训练
MANTIS: Multi-Axis News Transformations for Instance-Wise Stress Testing and Worst-Case Training in Fake News Detection
AI 导读
研究团队构建了 MANTIS-Bench 多轴呈现攻击基准，将原始新闻与写作风格、情感表达、传播框架三个维度的改写版本配对，并提出实例自适应对抗框架 MANTIS，实现零推理开销的动态最坏情况训练。
正文
Abstract:Automated fake news detection is vital on social media, where fake news is easily rewritten to fool detectors. However, existing approaches typically rely on superficial writing cues or single-style text rewrites, resulting in poor robustness under diverse cosmetic modifications. We construct MANTIS-Bench, a multi-axis presentation-attack benchmark that pairs original news with rewritten views across writing style, emotional expression, and dissemination framing. We further propose MANTIS, an instance-adaptive adversarial framework enabling dynamic worst-case training tailored to each news article with zero inference-time overhead. This reframes fake news defense from heuristic format smoothing into targeted, fact-invariant credibility assessment. Experiments on MANTIS-Bench show that MANTIS reduces the Union Attack Success Rate (UASR) by 3.55 percentage points relative to SheepDog on GossipCop and consistently outperforms prior single-axis defenses on Macro-F1 while maintaining competitive clean accuracy, demonstrating the effectiveness of multi-axis and instance-adaptive worst-case training.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.35475 [cs.CL] |
| (or arXiv:2610.35475v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35475 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dexin Liu [view email]
[v1]
Mon, 26 Oct 2026 14:09:10 UTC (715 KB)
来源：arXiv cs.CL · arxiv.org