arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.07673cs.LGcs.AI
收藏

使用因果表示推断去混淆偏差的多模态标题党检测

Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference

School of Artificial Intelligence, Sun Yat-sen University(中山大学人工智能学院);International Campus, Zhejiang University(浙江大学国际校区);WeChat Search Application Department, Tencent(腾讯微信搜索应用部);Pazhou Lab(琶洲实验室)

Jianxing Yu, Shiqi Wang, Han Yin, Zhenlong Sun, Ruobing Xie, Bo Zhang, Yanghui Rao

AI总结:

本文提出一种基于因果推断的去偏差方法,通过解耦多模态特征中的不变因子、因果因子和非因果噪声并消除噪声,构建鲁棒模型以检测伪装性强的多模态标题党帖子。

摘要:

本文关注检测网络上的标题党帖子。这些帖子常在混合模态中使用吸睛的虚假信息,误导用户点击以获利。这会影响用户体验,因此会被内容提供商屏蔽。为逃避检测,恶意创作者使用伎俩在诱饵帖子中加入无关的非诱饵内容,将其伪装成合法内容以欺骗检测器。这种内容通常与非诱饵标签存在偏差关系,而传统检测器倾向于基于简单的共现进行预测,而非掌握导致恶意行为的内在因素。这种伪偏差容易导致误判。为解决此问题,我们提出一种基于因果推断的去偏差新方法。我们首先采用多模态中的一组特征来表征帖子。考虑到这些特征常与未知偏差混淆,我们随后从中解耦出三类潜在因子,包括表示内在诱饵意图的不变因子;反映特定场景中欺骗模式的因果因子;以及非因果噪声。通过消除引起偏差的噪声,我们能利用不变和因果因子构建具有良好泛化能力的鲁棒模型。在三个流行数据集上的实验证明了我们方法的有效性。

英文摘要:

This paper focuses on detecting clickbait posts on the Web. These posts often use eye-catching disinformation in mixed modalities to mislead users to click for profit. That affects the user experience and thus would be blocked by content provider. To escape detection, malicious creators use tricks to add some irrelevant non-bait content into bait posts, dressing them up as legal to fool the detector. This content often has biased relations with non-bait labels, yet traditional detectors tend to make predictions based on simple co-occurrence rather than grasping inherent factors that lead to malicious behavior. This spurious bias would easily cause misjudgments. To address this problem, we propose a new debiased method based on causal inference. We first employ a set of features in multiple modalities to characterize the posts. Considering these features are often mixed up with unknown biases, we then disentangle three kinds of latent factors from them, including the invariant factor that indicates intrinsic bait intention; the causal factor which reflects deceptive patterns in a certain scenario, and non-causal noise. By eliminating the noise that causes bias, we can use invariant and causal factors to build a robust model with good generalization ability. Experiments on three popular datasets show the effectiveness of our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑