The Emergence of Deepfake Technology: A Review

By Mika Westerlund. 2019

943 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Media Technology, Generative Models, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Media Technology

In Generative Models

In Safety, Robustness & Interpretability

Citations in the corpus

CogView: Mastering Text-to-Image Generation via Transformers (2021, background): “Similar to Deepfake, CogView is vulnerable to malicious use [49] because of its controllable and strong capacity to generate images.”
Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services (2023, neutral): “training and inference have become more accessible as networks grow increasingly interconnected [9], [13].”
Teachers’ AI digital competencies and twenty-first century skills in the post-pandemic world (2023, background): “When students want to share their files publicly online, teachers need to be aware that the materials can be used to train AI on social media platforms (e.g., family photos, comments), which may lead to privacy issues (Westerlund, 2019).”
Synthetic Lies: Understanding AI-Generated Misinformation and Evaluating Algorithmic and Human Solutions (2023, background): “There have been some initial efforts to identify AI-generated misinformation from human-created datasets [78, 111].”
Improved Transformer for High-Resolution GANs (2021, background): “Additionally, such algorithms are vulnerable to malicious use [5], mainly through the development of deepfakes and other generated media meant to deceive the public [67], or as an image denoising technique that could be used for privacy-invading surveillance or monitoring purposes.”
AI-generated characters for supporting personalized learning and well-being (2021, background): “For example, celebrity faces have been swapped into pornographic videos 11 , the US president has been made to support criminal deception 73 , and the general population has been targeted with realistic fake news and harassment (or ‘troll-ing’) at levels beyond the capability of human detection 74 .”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, background): “In June 2019, a fake video of Facebook CEO Mark Zuckerberg was posted to Instagram by the Israeli advertising company “Canny” [52].”
Shap-E: Generating Conditional 3D Implicit Functions (2023, background): “On the positive side, it alleviates concerns regarding the potential use of our models to create convincing “DeepFakes” Prompt Samples “a doctor” “a nurse” “an engineer” [68].”
Machine learning and deep learning (2021, background): “…of “ deepfake ” content in the form of abusive speeches and misleading news to manipulate public opinions or distort financial markets is concerning (Westerlund 2019). properties such as the type of learning mechanisms (e.g., shallow ML vs. DL), the number and type of manually generated or…”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, background): “Moreover, GANs [330, 253] and re-lated data generation methods such as deepfake [331, 332, 333] have negative connotations since they can be used to imperson-ate individuals, by generating images, speech and related bio-metrics [334].”