SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11260 · 2024

Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.11260")
get_code_for_paper("2406.11260")
have("2406.11260")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.11260.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.11260.svg)](https://syntology.ai/paper/2406.11260)

Connect an agent — have() is free.