gen‑ai.news
← Back
Video

Pro-Kremlin deepfakes put surrender rhetoric in the mouths of Ukrainian lawmakers

Pro-Kremlin deepfakes put surrender rhetoric in the mouths of Ukrainian lawmakers

Pro-Kremlin Telegram channels have been distributing AI-generated deepfake videos that place surrender rhetoric in the mouths of real Ukrainian legislators. According to research by NewsGuard, the clips gathered around 130,000 views over a two-week period - a figure that illustrates how quickly fabricated content can reach a sizable audience through closed or semi-closed social platforms before fact-checkers have a chance to respond.

The videos appear designed to undermine domestic Ukrainian support for the war effort by making credible public figures seem to advocate for negotiations on terms favorable to Russia. This type of content does not need to fool every viewer to be effective. Even partial believability, or simple exposure before a debunking reaches the same audience, can introduce doubt and fragment trust in legitimate statements made by those same officials in the future.

Deepfake video quality has improved considerably over the past two years, and the barrier to producing a convincing face-swap or lip-sync manipulation has dropped significantly. Tools capable of generating this kind of content are now widely accessible, meaning the technical resources required to run an influence operation at this scale are no longer limited to well-funded state actors - though state backing can accelerate reach and targeting. The use of Telegram as a distribution channel is notable because the platform offers limited content moderation compared to larger Western social networks, making takedowns slower and less consistent.

The broader implication is one that researchers in disinformation and synthetic media have flagged repeatedly: the damage from a deepfake is not undone by a correction. When a fabricated video of a public figure is debunked, a portion of the audience that saw the original never encounters the rebuttal, and another portion discounts the rebuttal itself as part of the same information war. In a conflict where morale and public perception carry real strategic weight, the deliberate production of synthetic political speech represents a meaningful - if hard to quantify - front in the broader campaign.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

Video

Best AI Video Generation Models in 2026: Elo, Price per Second, Open Weights

The AI video generation landscape has shifted considerably over the past year, with native audio, longer clip lengths, and open-weights models now firmly part of the competitive field. A November 2026 ranking from Artificial Analysis's blind human-preference Elo arena pairs quality scores with API pricing to give a clearer picture of where each model stands. The result is a leaderboard that looks notably different from what it did in late 2025.

5 new Google Flow Tools designed by visual artists
Video

5 new Google Flow Tools designed by visual artists

Google has added five new tools to Flow, its AI-powered filmmaking platform, developed with input from working filmmakers and visual artists. The additions are aimed at giving creators more precise control over how their stories are visualized and produced. Each tool addresses a specific stage or challenge in the visual storytelling process.

Runway News | Closing the Gap Between Policy and Practice
Video

Runway News | Closing the Gap Between Policy and Practice

Runway has updated its content moderation policies to permit a broader range of dramatic and genre fiction content - including sword fights, shootouts, and horror - while keeping firm limits around genuine harm. The changes reflect an effort to bring the platform's written rules closer in line with what its systems actually allow in practice. Users can also now flag cases where moderation gets it wrong.