Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks

• URL: http://arxiv.org/abs/2310.10830v2
• Date: Tue, 20 Aug 2024 17:28:14 GMT
• Title: Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks
• Authors: Jiaying Wu, Jiafeng Guo, Bryan Hooi,
• Abstract summary: SheepDog is a style-robust fake news detector that prioritizes content over style in determining news veracity. SheepDog achieves this resilience through (1) LLM-empowered news reframings that inject style diversity into the training process by customizing articles to match different styles; (2) a style-agnostic training scheme that ensures consistent veracity predictions across style-diverse reframings; and (3) content-focused attributions that distill content-centric guidelines from LLMs for debunking fake news.
• Score: 60.14025705964573
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 for style-based attacks. Notably, the advent of powerful Large Language Models (LLMs) has empowered malicious actors to mimic the style of trustworthy news sources, doing so swiftly, cost-effectively, and at scale. Our analysis reveals that LLM-camouflaged fake news content significantly undermines the effectiveness of state-of-the-art text-based detectors (up to 38% decrease in F1 Score), implying a severe vulnerability to stylistic variations. To address this, we introduce SheepDog, a style-robust fake news detector that prioritizes content over style in determining news veracity. SheepDog achieves this resilience through (1) LLM-empowered news reframings that inject style diversity into the training process by customizing articles to match different styles; (2) a style-agnostic training scheme that ensures consistent veracity predictions across style-diverse reframings; and (3) content-focused veracity attributions that distill content-centric guidelines from LLMs for debunking fake news, offering supplementary cues and potential intepretability that assist veracity prediction. Extensive experiments on three real-world benchmarks demonstrate SheepDog's style robustness and adaptability to various backbones.

Related papers

• Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection [18.998947450697337]
  This study proposes adversarial style augmentation, AdStyle, to train a fake news detector. Our model's key mechanism is the careful use of LLMs to automatically generate a diverse yet coherent range of style-conversion attack prompts. Experiments show that our augmentation strategy improves robustness and detection performance when tested on fake news benchmark datasets.
  arXiv  Detail & Related papers  (2024-06-17T07:00:41Z)
• Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges [21.425647152424585]
  We propose a strong fake news attack method called conditional Variational-autoencoder-Like Prompt (VLPrompt) Unlike current methods, VLPrompt eliminates the need for additional data collection while maintaining contextual coherence. Our experiments, including various detection methods and novel human study metrics, were conducted to assess their performance on our dataset.
  arXiv  Detail & Related papers  (2024-03-27T04:39:18Z)
• SCStory: Self-supervised and Continual Online Story Discovery [53.72745249384159]
  SCStory helps people digest rapidly published news article streams in real-time without human annotations. SCStory employs self-supervised and continual learning with a novel idea of story-indicative adaptive modeling of news article streams.
  arXiv  Detail & Related papers  (2023-11-27T04:50:01Z)
• Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection [50.07850264495737]
  "Prompt-and-Align" (P&A) is a novel prompt-based paradigm for few-shot fake news detection. We show that P&A sets new states-of-the-art for few-shot fake news detection performance by significant margins.
  arXiv  Detail & Related papers  (2023-09-28T13:19:43Z)
• fakenewsbr: A Fake News Detection Platform for Brazilian Portuguese [0.6775616141339018]
  This paper presents a comprehensive study on detecting fake news in Brazilian Portuguese. We propose a machine learning-based approach that leverages natural language processing techniques, including TF-IDF and Word2Vec. We develop a user-friendly web platform, fakenewsbr.com, to facilitate the verification of news articles' veracity.
  arXiv  Detail & Related papers  (2023-09-20T04:10:03Z)
• Fake News Detectors are Biased against Texts Generated by Large Language Models [39.36284616311687]
  The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society. We present a novel paradigm to evaluate fake news detectors in scenarios involving both human-written and LLM-generated misinformation.
  arXiv  Detail & Related papers  (2023-09-15T18:04:40Z)
• Multiverse: Multilingual Evidence for Fake News Detection [71.51905606492376]
  Multiverse is a new feature based on multilingual evidence that can be used for fake news detection. The hypothesis of the usage of cross-lingual evidence as a feature for fake news detection is confirmed.
  arXiv  Detail & Related papers  (2022-11-25T18:24:17Z)
• Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation [105.20743048379387]
  We propose a novel framework for generating training examples informed by the known styles and strategies of human-authored propaganda. Specifically, we perform self-critical sequence training guided by natural language inference to ensure the validity of the generated articles. Our experimental results show that fake news detectors trained on PropaNews are better at detecting human-written disinformation by 3.62 - 7.69% F1 score on two public datasets.
  arXiv  Detail & Related papers  (2022-03-10T14:24:19Z)
• Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News [57.9843300852526]
  We introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles. In addition to the valuable insights gleaned from our user study experiments, we provide a relatively effective approach based on detecting visual-semantic inconsistencies.
  arXiv  Detail & Related papers  (2020-09-16T14:13:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.