This research explores how logical fallacies are used to spread misinformation on social media, focusing on the Ukrainian-Russian conflict as a case study.

• Investigates how manipulative content manifests in online forums
• Analyzes patterns of fallacious discourse in conflict-related discussions
• Demonstrates potential for generating synthetic examples to train detection systems
• Provides framework for identifying security threats in social media manipulation

This work has significant security implications by enhancing our ability to automatically detect and counter sophisticated manipulation campaigns in online spaces, particularly during geopolitical conflicts.

SLURG: Investigating the Feasibility of Generating Synthetic Online Fallacious Discourse