Search results for: Deepfake

Authors: Sushil Kumar Gupta, Atharva Joshi, Ayush Sonawale, Sachin Naik, Rajshree Khande

Abstract:

The usage of artificially created videos and audio by deep learning is a major problem of the current media landscape, as it pursues the goal of misinformation and distrust. In conclusion, the objective of this work targets generating a reliable deepfake detection model using deep learning that will help detect forged videos accurately. In this work, CelebDF v1, one of the largest deepfake benchmark datasets in the literature, is adopted to train and test the proposed models. The data includes authentic and synthetic videos of high quality, therefore allowing an assessment of the model’s performance against realistic distortions.

Keywords: deepfake detection, CelebDF v1, convolutional neural network (CNN), xception model, data augmentation, media manipulation

Procedia PDF Downloads 15

Authors: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 152

Authors: Noor Azwa Azreen Binti Abd. Aziz, Muhamad Zaim Bin Mohd Rozi

Abstract:

Moving towards the 4th Industrial Revolution, artificial intelligence (AI) is now more popular than ever. This subject is gaining significance every day and is continually expanding, often merging with other fields. Instead of merely being passive observers, there are benefits to understanding modern technology by delving into its inner workings. However, in a world teeming with digital information, the impact of AI on the spread of disinformation has garnered significant attention. The dissemination of inaccurate or misleading information is referred to as misinformation, posing a serious threat to democratic society, public debate, and individual decision-making. This article delves deep into the connection between AI and the dissemination of false information, exploring its potential, risks, and ethical issues as AI technology advances. The rise of AI has ushered in a new era in the dissemination of misinformation as AI-driven technologies are increasingly responsible for curating, recommending, and amplifying information on online platforms. While AI holds the potential to enhance the detection and mitigation of misinformation through natural language processing and machine learning, it also raises concerns about the amplification and propagation of false information. AI-powered deepfake technology, for instance, can generate hyper-realistic videos and audio recordings, making it increasingly challenging to discern fact from fiction.

Keywords: artificial intelligence, digital information, disinformation, ethical issues, misinformation

Procedia PDF Downloads 97

Authors: Raymond Xu, Cindy Jingru Wang

Abstract:

Social media has become a globally connected and influencing platform. Social media data, such as tweets, can help predict the spread of pandemics and provide individuals and healthcare providers early warnings. Public psychological reactions and opinions can be efficiently monitored by AI models on the progression of dominant topics on Twitter. However, statistics show that as the coronavirus spreads, so does an infodemic of misinformation due to pandemic-related factors such as unemployment and lockdowns. Social media algorithms are often biased toward outrage by promoting content that people have an emotional reaction to and are likely to engage with. This can influence users’ attitudes and cause confusion. Therefore, social media is a double-edged sword. Combating fake news and biased content has become one of the essential tasks. This research analyzes the variety of methods used for fake news detection covering random forest, logistic regression, support vector machines, decision tree, naive Bayes, BoW, TF-IDF, LDA, CNN, RNN, LSTM, DeepFake, and hierarchical attention network. The performance of each method is analyzed. Based on these models’ achievements and limitations, a multi-dimensional AI framework is proposed to achieve higher accuracy in infodemic detection, especially pandemic-related news. The model is trained on contextual content, images, and news metadata.

Keywords: artificial intelligence, fake news detection, infodemic detection, image recognition, sentiment analysis

Procedia PDF Downloads 265