Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection
The spread of fake news harms individuals and presents a critical social challenge that must be addressed. Although numerous algorithmic and insightful features have been developed to detect fake news, many of these features can be manipulated with style-conversion attacks, especially with the emergence of advanced language models, making it more difficult to differentiate from genuine news. This study proposes adversarial style augmentation, AdStyle, designed to train a fake news detector that remains robust against various style-conversion attacks. The primary mechanism involves the strategic use of LLMs to automatically generate a diverse and coherent array of style-conversion attack prompts, enhancing the generation of particularly challenging prompts for the detector. Experiments indicate that our augmentation strategy significantly improves robustness and detection performance when evaluated on fake news benchmark datasets.
Code (1)
Tasks
Fake News DetectionLanguage ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
Exploring Adversarial Fake Images on Face Manifold
Images synthesized by powerful generative adversarial network (GAN) based methods have drawn moral and privacy concerns. Although image forensic models have reached great performance in detecting fake images from real on…
Adversarial AttackDeepFake DetectionFace SwappingGenerative Adversarial NetworkRobust Fake News Detection using Large Language Models under Adversarial Sentiment Attacks
Misinformation and fake news have become a pressing societal challenge, driving the need for reliable automated detection methods. Prior research has highlighted sentiment as an important signal in fake news detection, e…
Fake News DetectionSemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data
Although convolutional neural networks have been proven to be an effective tool to generate high quality maps from remote sensing images, their performance significantly deteriorates when there exists a large domain shif…
Data AugmentationDomain AdaptationImage-to-Image TranslationSemantic Segmentation+1Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks
It is commonly perceived that fake news and real news exhibit distinct writing styles, such as the use of sensationalist versus objective language. However, we emphasize that style-related features can also be exploited …
ArticlesFact CheckingFake News DetectionTargeted Augmented Data for Audio Deepfake Detection
The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, whi…
Audio Deepfake DetectionDeepFake DetectionFace Swapping