Tokyo Report | Security | East Asia

AI Is Lowering the Barriers to China’s Information Warfare Against Japan

China-linked influence operators are increasingly using AI to craft more effective disinformation campaigns. 

Japan’s Ministry of Defense recently released its 2026 Defense of Japan white paper, once again drawing attention to China’s rapid advances in artificial intelligence and their implications for the regional security environment. Yet the most immediate danger to Japan may not come from AI’s application to conventional military systems. Generative AI is also lowering the barriers for Chinese information operations targeting Japanese society.

In late 2025, Prime Minister Takaichi Sanae made comments in the Diet linking a Taiwan contingency to Japan’s own security. Since then, disinformation targeting Japanese political figures and domestic issues has grown – not only in volume but also in sophistication. Research by organizations including the Sasakawa Peace Foundation and OpenAI suggests that China-linked influence operators are increasingly using AI to adapt their activities to Japan’s online environment and improve the efficiency of their operations.

AI is beginning to erode what was once one of the most obvious weaknesses of Chinese information operations against Japan: the linguistic and cultural barrier. Content that once featured grammatical mistakes, awkward translations and unnatural expressions is becoming harder for ordinary users to identify at a glance. 

If these capabilities are deployed to interfere with elections, discredit politicians or amplify social divisions, their effects could extend far beyond any single piece of false information.

A special report by Nikkei in February found that more than 400 China-linked social media accounts spread negative content about Takaichi during Japan’s House of Representatives election. Separately, the Yomiuri Shimbun, citing research by Japan Nexus Intelligence, reported that under a different set of criteria, thousands of coordinated accounts on X were involved in sharing and amplifying related content.

The narratives did not focus solely on attacking Takaichi personally. They also linked Japan’s efforts to strengthen its defense capabilities with concerns over social welfare, seeking to promote the argument that military expansion was coming at the expense of ordinary people.

In the past, such accounts often left obvious clues. Some had been created only recently. Their Japanese reflected Chinese word order and linguistic habits, while others mixed simplified Chinese characters with Japanese usage. AI-generated images also frequently contained visual errors that made them relatively easy to identify.

Those weaknesses, however, are becoming less pronounced.

The Sankei Shimbun has continued to track PAPERWALL, a China-linked information network that includes 15 websites masquerading as Japanese news outlets. The continued operation of these sites, and the broader ecosystem surrounding them, points toward an increasingly localized approach to influence operations. Improvements in language, imagery, and the appearance of fake news sites are making it more difficult for ordinary readers to distinguish legitimate sources from fabricated ones.

A report released by OpenAI in February offered another important clue. The company found that China-linked actors had used ChatGPT to assist in planning an online influence campaign targeting Takaichi. Influence actors appear willing to incorporate different AI systems into their existing workflows whenever those tools make their operations more effective.

What matters is not the nationality of the model. What matters is that........

© The Diplomat