Does Deception Leave a Content Independent Stylistic Trace?
Does Deception Leave a Content Independent Stylistic Trace?
复制标题
欺骗是否会留下内容独立的风格痕迹？
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Rakesh M. Verma
中科院分区：
文献类型：
--
作者：
Victor Zeng;Xuting Liu;Rakesh M. Verma
最近的一项调查表明，人们对欺骗行为并没有普遍的语言暗示。由于互联网社会受到网络钓鱼和假新闻等欺骗性攻击的困扰，这一说法意味着我们必须为每种攻击构建单独的数据集和检测器。这也意味着，当一个新的骗局（例如，COVID）到来时，我们必须从头开始数据收集、注释和模型构建的整个过程。在本文中，我们通过构建一个高质量的独立于域的欺骗数据集并调查一个模型是否可以在多种形式的欺骗上表现良好来测试这一说法。
A recent survey claims that there are em no general linguistic cues for deception. Since Internet societies are plagued with deceptive attacks such as phishing and fake news, this claim means that we must build individual datasets and detectors for each kind of attack. It also implies that when a new scam (e.g., Covid) arrives, we must start the whole process of data collection, annotation, and model building from scratch. In this paper, we put this claim to the test by building a quality domain-independent deception dataset and investigating whether a model can perform well on more than one form of deception.
DOI：
10.1145/3319535.3363267
发表时间：
2019-11
期刊：
Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security
影响因子：
--
作者：
Rakesh M. Verma;Victor Zeng;Houtan Faridi
通讯作者：
Rakesh M. Verma;Victor Zeng;Houtan Faridi