Tutorial 14: Synthetic Realities: Impact, Advancements, and Ethical Considerations

Speakers

  • Dr. Gabriel Bertocco (Artificial Intelligence Lab., Recod.ai, Institute of Computing, University of Campinas (Unicamp), Brazil)
  • Prof. Dr. Anderson Rocha (Institute of Computing, Recod.ai, University of Campinas (Unicamp), Brazil)

 

Abstract

In this tutorial, we will explore the burgeoning landscape of synthetic realities, their impact, technological advancements, and ethical quandaries. Synthetic realities provide innovative solutions and opportunities for immersive experiences in various sectors, including education, healthcare, and commerce. However, these advances also present substantial challenges, such as the propagation of misinformation, privacy concerns, and ethical dilemmas. We will discuss the specifics of synthetic media, including deepfakes and their generation techniques, modern AI-empowered multimedia manipulations, (mis)information, and (dis)information. We will also touch upon the imperative need for robust detection and explainable methods to combat the potential misuse of such technologies. We will show the dual-edged nature of synthetic realities and advocate for interdisciplinary research, informed public discourse, and collaborative efforts to harness their benefits while mitigating risks. We also present future trends and perspectives of synthetic realities. This tutorial contributes to the discourse on the responsible development and application of artificial intelligence and synthetic media in modern society. We expect graduate students, faculty, and industrial researchers/engineers with entry-level knowledge in machine learning to attend to this tutorial.

 

Target Audience

We expect graduate students, faculty, and industrial researchers/engineers with entry-level knowledge in machine learning and basic concepts about deep learning. Basically, the audience is expected to know concepts about Convolutional Neural Networks (CNNs), Transformers, Generative Adversarial Networks (GANs), Diffusion Models, and general training and evaluation pipelines. Some basics concepts in Natural Language Processing are not required, but helps the audience to better understand some presented methods.

 

Outline and Description of the Tutorial

1. Introduction to Synthetic Realities

2. Applications of Synthetic Realities in advertising, entertainment and health campaigns

3. Synthetic Realities synthesis and cases of study

  • Face Swap
  • Face Reenactment (Puppet-mastery)
  • Lip-syncing
  • Entire Scene Synthesis
  • Face Attribute Manipulation
  • Text-to-Speech Synthesis
  • Voice Conversion
  • Text generation with Large-Language Models (LLMs)

4. Detection methods

  • Deepfake Detection
  • Generalizable Deepfake Detection
  • Self-Supervised Learning for Deepfake Detection
  • Detection of LLM-generated content

5. Social, Technical and Political Challenges

6. Legislation

7. Education and Standardization

8. Future perspectives

We will cover real cases of study where people were fooled by deepfakes causing financial loss or had their integrity prejudiced. Upon these cases, we will show state-of-the-art generators and detectors. In the generator’s side, we will cover the main generation strategies such as Face Swap, Face Reenactment, Lip Syncing, Facial Attribute Manipulation, Entire Face Synthesis, Text-to-Speech, Voice Conversion, and LLM-based text generation. From the detector’s side, we will delve into different solutions, and discuss their explainability and deployability in real-world applications. We will also cover legislation and political aspects of the employment of synthetic realities in society. We expect the audience to walk away with:

  1. Awareness about the good and bad impacts of Synthetic Realities.
  2. Technical principles of generation and detection of Synthetic Realities in image, audio, and text modalities.
  3. Political and economic opportunities that arise from this technology.
  4. How to use the Synthetic Realities technologies in a responsible and accountable manner.
  5. Social implications of such technologies in terms of legislation and society education and literacy.

 

Reading List

Please, find below related publications to the tutorial’s topic:

  • D. Moreira, S. Marcel and A. Rocha, “Synthetic Realities and Artificial Intelligence-Generated Contents,” in IEEE Security & Privacy Special Issue, vol. 22, no. 3, pp. 7-10, May- June 2024.
  • Cardenuto, João Phillipe, Jing Yang, Rafael Padilha, Renjie Wan, Daniel Moreira, Haoliang Li, Shiqi Wang, Fernanda Andaló, Sébastien Marcel, and Anderson Rocha. “The age of synthetic realities: Challenges and opportunities.” APSIPA Transactions on Signal and Information Processing 12, no. 1, 2023.
  • C. Kong, A. Luo, S. Wang, H. Li, A. Rocha and A. C. Kot, “Pixel-Inconsistency Modeling for Image Manipulation Localization,” in IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 6, pp. 4455-4472, June 2025.
  • C. Kong, B. Chen, H. Li, S. Wang, A. Rocha and S. Kwong, “Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-Level Telltales,” in IEEE Transactions on Information Forensics and Security, vol. 17, pp. 1741-1756, 2022.
  • Wang, Yifei. “Synthetic realities in the digital age: Navigating the opportunities and challenges of ai-generated content.” Authorea Preprints (2023).
  • Stroebel, Laura, Mark Llewellyn, Tricia Hartley, Tsui Shan Ip, and Mohiuddin Ahmed. “A systematic literature review on the effectiveness of deepfake detection techniques.” Journal of Cyber Security Technology 7, no. 2 (2023): 83-113.
  • Sun, Yanshen, Jianfeng He, Limeng Cui, Shuo Lei, and Chang-Tien Lu. “Exploring the deceptive power of llm-generated fake news: A study of real-world detection challenges.” arXiv preprint arXiv:2403.18249 (2024).
  • Cavus, Nadire, Murat Goksu, and Bora Oktekin. “Real-time fake news detection in online social networks: FANDC Cloud-based system.” Scientific Reports 14, no. 1 (2024): 25954.
  • Guo, Quanjiang, Zhao Kang, Ling Tian, and Zhouguo Chen. “Tiefake: Title-text similarity and emotion-aware fake news detection.” In 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1-7. IEEE, 2023.
  • Yang, Jing, and Anderson Rocha. “Take it easy: Label-adaptive self-rationalization for fact verification and explanation generation.” In 2024 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1-6. IEEE, 2024.
  • Yan, Zhiyuan, Yong Zhang, Yanbo Fan, and Baoyuan Wu. “Ucf: Uncovering common features for generalizable deepfake detection.” In Proceedings of the IEEE/CVF international conference on computer vision, pp. 22412-22423. 2023.
  • Qiao, Tong, Shichuang Xie, Yanli Chen, Florent Retraint, and Xiangyang Luo. “Fully unsupervised deepfake video detection via enhanced contrastive learning.” IEEE Transactions on Pattern Analysis and Machine Intelligence 46, no. 7 (2024): 4654-4668.

 

Vertical

Generative AI Models, AI in Education and Agentic AI

 

Timeline

4 hours