# Deepfake

Scam AI is a platform focused on detecting AI fraud. Through advanced technological methods, it can rapidly analyze and identify deepfakes, voice cloning, and other potential fraudulent information. In today’s fast-developing AI landscape, the speed and concealment of misinformation have significantly increased, making Scam AI a necessary protective tool for users. It requires no technical background, enabling users to quickly verify the authenticity of various content, helping them remain vigilant in the digital world and avoid falling victim to fraud. Currently, the platform is in beta testing, aiming to continually improve its detection algorithms and user experience.

The AI Video Quiz is an online test created by the Kapwing team, designed to educate the public on how to differentiate between real videos and AI-generated fakes. Through this quiz, users can learn about the latest advancements in AI video editing technology and enhance their vigilance against deepfake videos. This test prompts users to judge the authenticity of videos featuring public figures, fostering reflection on the application of AI technology in video production.

SafeEar is an innovative audio depth detection framework that can identify deep audio without relying on speech content. The framework employs a neural audio codec design to separate semantic and acoustic information from audio samples, using solely acoustic features (such as prosody and timbre) for depth detection, thereby safeguarding the privacy of speech content. SafeEar enhances the detector's capabilities by augmenting the codec in real-world scenarios, enabling it to recognize various forms of deep audio. Extensive experiments conducted on four benchmark datasets demonstrate that SafeEar is highly effective in detecting various deep technologies, achieving a minimum equal error rate (EER) of 2.02%. Moreover, it protects speech content in five languages from deciphering by both machine and human auditory analysis, as validated by our user studies revealing a word error rate (WER) exceeding 93.93%. Additionally, SafeEar has established a benchmark for anti-deep and anti-content recovery assessments, laying the groundwork for future research in audio privacy protection and depth detection.