Deep fake technology can be used to create realistic intimidation activities in a variety of ways: ### Video forgery 1. **Fake threatening videos** - Attackers use deep fake software to transplant other people's facial, voice and other features into fake threatening speech videos. For example, the face of a well-known person is replaced with an image claiming to violently retaliate or destroy a specific target, accompanied by extremely threatening words. If such a video is spread to the target object or related groups, it is easy to cause panic and anxiety. - Deep fake technology can finely adjust details such as facial expressions and body movements to make the fake video look very realistic and difficult to distinguish between true and false. Even if the target object or recipient knows that there may be deep fakes, the realistic visual and auditory presentation will still have a strong psychological impact and induce fear. 2. **Tampering with surveillance videos** - Deep fake tampering of surveillance videos of specific places. For example, the normal scene in the surveillance screen is modified to show a fake picture of a terrorist breaking in or carrying out sabotage activities. Then the tampered video is spread through various channels, which may cause people in the relevant area to panic and cause social disorder. - Deep fakes can subtly change the light and shadow, character behavior and other elements in the video to blend with the style and characteristics of the original surveillance video, increase the credibility of the video, and further enhance the intimidation effect. ### Audio fakes 1. **Simulated threatening voice** - Use deep fake technology to simulate threatening voice messages. For example, imitate an authority figure or a familiar voice and say threatening content such as "You will face serious consequences if you don't do what I say..." This realistic voice fake can be sent to the target object through phone calls, voice messages, etc., causing direct psychological pressure on the other party. - The fake voice can accurately imitate the tone, speed, accent and other characteristics of the target voice, making it difficult for the recipient to distinguish the authenticity, making it easier for the recipient to believe the authenticity of the threatening information, generating fear and anxiety, and affecting their normal life and decision-making. 2. **Creating false audio events** - Forge some audio that sounds like violent and dangerous events happening in a specific area, such as explosions, gunshots, etc., and at the same time add false on-site descriptions and threatening words. Through social media, online audio platforms and other channels, people are misled into believing that these horrific events are actually happening, thus causing panic and anxiety among the public and disrupting the normal rhythm of social life. The abuse of deep fake technology makes it relatively easy to create realistic intimidation activities, posing a serious security threat to individuals, organizations and even society.