Redakcja Choose TV
The development of generative artificial intelligence has made creating realistic videos simpler than ever before. At the same time, it is becoming increasingly difficult to distinguish real recordings from AI-generated material. The problem of deepfakes is becoming an ever greater challenge for the media, companies and internet users. NVIDIA has moved to address this issue by unveiling a new AI tool for detecting manipulated footage. The solution was presented at the SIGGRAPH 2026 conference. The company emphasises that the technology is intended to support the verification of content, not to replace human work.
Synthetic Video Detector analyses video in real time
NVIDIA's new tool, called Synthetic Video Detector, was developed to detect material generated or altered by artificial intelligence. The system analyses footage frame by frame and assigns a probability that AI was used in creating the video. According to the manufacturer, analysing Full HD material takes just 22 milliseconds on machines equipped with RTX GPUs. This enables near real-time use. The tool has been released as part of the NVIDIA NIM Microservices platform, allowing organisations to easily integrate it with existing systems. The company notes that the technology is intended to serve as an additional layer of protection for newsrooms, broadcasters and enterprises. Its purpose is to quickly verify material before publication. NVIDIA emphasises that it does not replace traditional journalistic analysis or the methods used by digital forensics specialists.
High effectiveness should help in the fight against the growing wave of disinformation
According to figures presented by NVIDIA, the new solution achieves effectiveness of up to 92 per cent when analysing uncompressed video. For recordings compressed by around 15 per cent, accuracy falls to 87 per cent, while under heavier compression of 50 per cent it reaches about 82 per cent. Compression remains one of the biggest challenges for systems detecting deepfakes, because platforms such as YouTube, TikTok and Instagram automatically reduce the quality of uploaded content. NVIDIA also says that the Synthetic Video Detector achieved top results in the AI GVD Bench benchmark, used to compare tools that detect synthetic video. The company also plans to integrate the technology with the Wowza Intelligence Video Framework platform, which operates in over 35,000 deployments across 170 countries. The manufacturer stresses, however, that the tool is not a perfect solution and should support, not replace, human assessment of material. As generative artificial intelligence develops, the sophistication of fake recordings is also increasing. The fight against disinformation will therefore require the simultaneous advancement of detection technologies and responsible human work.
Synthetic Video Detector shows that artificial intelligence can be used not only to create realistic content but also to detect it. Thanks to very fast performance and high accuracy, NVIDIA's new solution could become an important tool in the fight against deepfakes and online disinformation. The manufacturer emphasises, however, that even the best algorithms will not replace rigorous human verification of information.
source: digitaltrends
