Generic visuality of war? How image-generative AI models (mis)represent Russia's war against Ukraine

2025-12-06

AI Summary

This study investigates how geopolitical contexts shape generative AI’s visual representations of war, focusing on divergent outputs from U.S.-developed Midjourney and Russia-developed Kandinsky when prompted with Ukraine-Russia War–related queries. Method: Employing prompt engineering, large-scale image auditing, visual content analysis, and aesthetic feature encoding, the work conducts the first systematic cross-Western/non-Western comparative study of foundation models. Contribution/Results: Both models significantly attenuate graphic violence while reinforcing stereotypical imagery—resulting in abstracted, homogenized war depictions that erode historical specificity. Output disparities stem from geographically embedded training data and value-laden algorithmic design, revealing how generative AI is accelerating the institutionalization of structurally biased “war aesthetics.” The findings provide empirical grounding and a methodological framework for AI content governance and critical geopolitically informed technology studies.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

The rise of generative AI (genAI) can transform the representation of different aspects of social reality, including modern wars. While scholarship has largely focused on the military applications of AI, the growing adoption of genAI technologies may have major implications for how wars are portrayed, remembered, and interpreted. A few initial scholarly inquiries highlight the risks of genAI in this context, specifically regarding its potential to distort the representation of mass violence, particularly by sanitising and homogenising it. However, little is known about how genAI representation practices vary between different episodes of violence portrayed by Western and non-Western genAI models. Using the Russian aggression against Ukraine as a case study, we audit how two image-generative models, the US-based Midjourney and the Russia-based Kandinsky, represent both fictional and factual episodes of the war. We then analyse the models' responsiveness to the war-related prompts, together with the aesthetic and content-based aspects of the resulting images. Our findings highlight that contextual factors lead to variation in the representation of war, both between models and within the outputs of the same model. However, there are some consistent patterns of representation that may contribute to the homogenization of war aesthetics.

Problem

• Analyzes how AI models represent war episodes
• Compares Western and non-Western AI war depictions
• Examines aesthetic homogenization risks in AI-generated war imagery

Innovation

• Auditing US and Russian AI image models
• Analyzing war representation variations
• Identifying homogenization patterns in war aesthetics