Generative AI & Deepfake Detection Software
Deepfakes introduce a new form of disinformation, presenting altered or fabricated content designed to influence perspectives. With the rise of Generative AI, deepfake technology has become widely accessible. However, this accessibility also raises concerns about potential abuse. This is why we developed our AI detection tool to safeguard against such abuse.
Detecting Generative AI and Deepfakes
In addition to traditional deepfakes, our detection capabilities also extend to content generated by other generative AI models, such as Dall-E and Midjourney. Our technology identifies the subtle nuances and patterns that distinguish AI-generated images from real photography, ensuring that you can reliably discern authentic content from synthetic creations.
Here are examples of the output from our detection tools
Types of Deepfakes
Rather than just one technique there are various types of deepfakes. We can regard deepfakes as a collective name for audiovisual data altered by smart algorithms instead of manual labour. We distinguish 3 types of deepfakes: FaceSwap, StyleGANs and Deep Puppetry.
Note that deepfakes can be made of all visual data. There are for example horse StyleGANs. However, we focus on human faces.
Learn more
FaceSwaps
The face of the donor file is copied and pasted, it mimics the emotions and motions of the source file.
StyleGANs
Generated faces by a neural network that learned with a big dataset to create new unique faces.
Deep Puppetry
The person in the source file mimics the emotions and motions of the donor file.
1 sec analysis
With our API-integration
100%
Understandable results
Deepfakes & Generative AI: The New Digital Threat
Digital Identities & Fake Profiles
We're familiar with trolls and fake profiles spreading fakes news. Now, they are amplified by deepfakes. With our AI detection tools, we can better detect and prevent the spread of false information
Real-time AI manipulation
Are you sure the person on the other side of the screen is the one you think you're talking to? It is now possible to create deepfakes in real-time. With our AI detection tool, we help check and safeguard against d
Fake content
What if a video were to be released of people saying things they have never said? How would you prove it is fake? Thus, deepfake detection and identity verification are vital for discerning truth from fiction
How are deepfakes made?
1. Training with AI Detection
To craft deepfakes, a neural network learns from numerous images or videos. With more data, it produces better deepfakes. Today, even non-techies can use pre-trained networks that can be found and bought online.
2. Alteration
Once trained, this program alters videos. It mimics movements from one video and applies them to another by adjusting pixels. Sometimes, these changes result in noticeable "artifacts."
3. Disguising
The program can hide these artifacts to deceive AI detectors. It might reduce video quality or employ advanced methods like "blackbox" attacks, making AI detection and identity verification tools crucial in spotting such deceptions.
How we detect deepfakes
Insights
The DeepDetector pinpoints the pixels in the image the software used to determine whether the analysed footage is a deepfake or authentic. This analysis is called the 'activation map'. With this analysis the users of the software can understand the conclusion and evaluate the decision of the software themselves maintaining their autonomy.
Training
The DeepDetector is trained on a dataset of deepfake and authentic images. During training it learns to distinguish authentic images or videos from deepfaked ones. As more deepfake techniques are invented, we will increase the datasets used for training the DeepDetector. This ensures the DeepDetector will always stay up-to-date with the latest advancements in deepfake generation.
Classifying
The DeepDetector is a neural network. It outputs probabilities which indicate whether the input is deemed a deepfake or not. Higher percentages indicate that the software is more confident of its decision.
.webp)
Other ways to spot deepfakes
Deepfakes are becoming higher in quality while being easier and cheaper to make. It consequently becomes harder to spot deepfakes with the naked eye. However, at this moment you can still look for several typical graphic inconsistencies (called artefacts) in deepfakes, the typical artefacts to look for are listed below.
Colour transition
In neural puppetry and faceswap deepfakes, the face is manipulated. Sometimes a hard colour transition can be seen on the edges of the area the deepfake software manipulated
Accessories
Items like glasses might look convincing at first, but when looked closer, might actually contain some artefacts
Blurry background or context
StyleGAN deepfakes are good in making faces, but bad at creating context that make sense. Check the background and clothing, for example, to see if these make any sense
Unnatural looking eyes
Eyes are rather hard to deepfake due to its complexity. Check if the reflections in the eyes have the same angle. Does the person in the video blink? Are the irises of both eyes equally large?
What else can you do when in doubt?
Think critically
Does the footage spark an emotional response for you? Disinformation often tends to influence your opinion and does frequently do so by sparking negative emotions regarding specific people. Do you react emotionally to the footage? Stay calm and check the information more closely. By thinking critically one could potentially question the footage on its authenticity.
Synthetic data & deepfakes
There are several fact checking websites like Snopes and Bellingcat that you can visit for free. For faceswap and neural puppetry deepfakes a source file is needed to create the deepfake. If in doubt, you can reverse image or video search the image or video. And, of course, you can always request a demo version of our online tool, DeepDetector!
