The misuse of deep learning-based facial manipulation poses a potential threat to civil rights. To prevent this fraud at its source, proactive defense technology was proposed to disrupt the manipulation process by adding invisible adversarial perturbations into images, making the forged output unconvincing to the observer. However, their non-directional disruption of the output may result in the retention of identity information of the person in the image, leading to stigmatization of the individual. In this paper, we propose a novel universal framework for combating facial manipulation, called ID-Guard. Specifically, this framework requires only a single forward pass of an encoder-decoder network to generate a cross-model universal adversarial perturbation corresponding to a specific facial image. To ensure anonymity in manipulated facial images, a novel Identity Destruction Module (IDM) is introduced to destroy the identifiable information in forged faces targetedly. Additionally, we optimize the perturbations produced by considering the disruption towards different facial manipulations as a multi-task learning problem and design a dynamic weights strategy to improve cross-model performance. The proposed framework reports impressive results in defending against multiple widely used facial manipulations, effectively distorting the identifiable regions in the manipulated facial images. In addition, our experiments reveal the ID-Guard's ability to enable disrupted images to avoid face inpaintings and open-source image recognition systems.

A research group from the Moscow Institute of Physics and Technology (MIPT) and Russian Internet giant Yandex have proposed a novel image-to-image translation model that uses synthesized input data to enable a "paired" training approach. The model outperforms existing methods in image manipulation and offers researchers a possible solution to the scarcity of paired datasets. Generative adversarial networks (GAN) are one of the most effective methods for realistic image generation. GANs provide many opportunities for image manipulation and morphing, such as transferring the age or gender of a human face. Network architecture types most commonly used for transforming a human face are trained on either paired images (same subject, different time) or unpaired data.

At a time when facial manipulation tools, deepfakes and fake facial images are more advanced and common than ever before, Adobe, the multinational American computer software company, has trained AI to differentiate these fakes from original facial photos. A team of researchers from Adobe and UC Berkeley in California, U.S., have worked together to create this tool. The aim of their work is to restore faith in digital media, in a day and age when countless fakes and touch ups occur. The team studied Adobe's Photoshop feature called Face Away Liquify, which is meant to change people's faces, eyes and mouths. Later, they trained a convolutional neural network (CNN), used to analyze visual imagery, to pick up the changes made to the faces in the images.

Adobe, along with researchers from the University of California, Berkeley, have trained artificial intelligence (AI) to detect facial manipulation in images edited using the Photoshop software. At a time when deepfake visual content is getting commoner and more deceptive, the decision is also intended to make image forensics understandable for everyone. "This new research is part of a broader effort across Adobe to better detect image, video, audio and document manipulations," the company wrote in a blog post on Friday. As part of the programme, the team trained a convolutional neural network (CNN) to spot changes in images made with Photoshop's "Face Away Liquify" feature, which was intentionally designed to change facial features like eyes and mouth. On testing, it was found that while human eyes were able to judge the altered face 53 percent of the time, the the trained neural network tool achieved results as high as 99 percent.