Explore papers
Filter by research area, year and venue. Every filter is in the address bar, so you can share a view as a link.
LLMs & generative AIDetection methods
SINcon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor DetectionMessage Propagation Tree (MPT) based rumor detection models are vulnerable to LLM-generated malicious message injection attacks that alter tree topology and semantics. The paper proposes SINcon, a contrastive learning defense that regularizes models to assign similar predictive influence to nodes of different importance levels,…
LLMs & generative AIDetection methods
Challenges and Innovations in LLM-Powered Fake News Detection: A Synthesis of Approaches and Future DirectionsThis survey synthesizes recent advances in applying large language models to fake news detection on social media. The review covers four major LLM-based frameworks (MiLk-FD, FND-LLM, DAFND, SheepDog), identifies critical challenges around multimodal integration, adversarial robustness, scalability, and interpretability, and proposes…
Deepfakes & multimodalDatasets & evaluation
VLDBench: Evaluating Multimodal Disinformation with Regulatory AlignmentVLDBench is the first large-scale human-verified benchmark for multimodal disinformation detection, comprising 31,339 news articles paired with images across 13 topical categories. Evaluation of 9 LLMs and 10 VLMs shows vision-language models substantially outperform text-only baselines (e.g., LLaMA-3.2-11B-Vision: 74.82% accuracy), but…
Detection methodsLLMs & generative AI
Propasafe: A BERT-based offline tool for propaganda detectionOriginal privacy-focused, offline browser extension using fine-tuned BERT on the Propaganda Techniques Corpus for sentence-level propaganda classification. No online inference required; binary classification (propaganda or non-propaganda).