FolioStart free

Computer Science · Literature

Research papers on Deepfake detection

Recent and highly-cited academic work on deepfake detection, gathered from Semantic Scholar, CrossRef and OpenAlex.

Search all 200M+ papers on this topic, free →Or track new deepfake detection papers automatically as they publish

  1. SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

    Zhenglin Huang, Jinwei Hu, Xiang-Tai Li, et al. · 2024 · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 183 citations

    The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode trust in digital content, resulting in severe repercussions. Despite some progress, academia has not yet created a large and diversified deepfake detection dataset for social media, nor has it devised an effective solution to address this issue. In this paper, we introduce the Social media Image Detection dataSet (SID-Set), which offers three key advantages: (1) extensive volume, featuring 300K AI-generated/tampered and authentic images with comprehensive

    Save this paper

  2. The Deepfake Detection Dilemma: A Multistakeholder Exploration of Adversarial Dynamics in Synthetic Media

    Claire R. Leibowicz, Sean McGregor, Aviv Ovadya · 2021 · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · 32 citations

    Synthetic media detection technologies label media as either synthetic or non-synthetic and are increasingly used by journalists, web platforms, and the general public to identify misinformation and other forms of problematic content. As both well-resourced organizations and the non-technical general public generate more sophisticated synthetic media, the capacity for purveyors of problematic content to adapt induces a detection dilemma : as detection practices become more accessible, they become more easily circumvented. This paper describes how a multistakeholder cohort from academia, technology platforms, media entities, and civil society organizations active in synthetic media detection

    Save this paper

  3. Novel Deepfake Image Detection with PV-ISM: Patch-Based Vision Transformer for Identifying Synthetic Media

    Orkun Çınar, Yunus Doğan · 2025 · Applied Sciences · 13 citations

    This study presents a novel approach to the increasingly important task of distinguishing AI-generated images from authentic photographs. The detection of such synthetic content is critical for combating deepfake misinformation and ensuring the authenticity of digital media in journalism, forensics, and online platforms. A custom-designed Vision Transformer (ViT) model, termed Patch-Based Vision Transformer for Identifying Synthetic Media (PV-ISM), is introduced. Its performance is benchmarked against innovative transfer learning methods using 60,000 authentic images from the CIFAKE dataset, which is derived from CIFAR-10, along with a corresponding collection of images generated using Stabl

    Save this paper

  4. Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems

    Naseem Khan, T. Nguyen, Amine Bermak, et al. · 2025 · ArXiv · 11 citations

    The rapid advancement of Generative Artificial Intelligence has fueled deepfake proliferation-synthetic media encompassing fully generated content and subtly edited authentic material-posing challenges to digital security, misinformation mitigation, and identity preservation. This systematic review evaluates state-of-the-art deepfake detection methodologies, emphasizing reproducible implementations for transparency and validation. We delineate two core paradigms: (1) detection of fully synthetic media leveraging statistical anomalies and hierarchical feature extraction, and (2) localization of manipulated regions within authentic content employing multi-modal cues such as visual artifacts an

    Save this paper

  5. Deepfake Satire and the Possibilities of Synthetic Media

    Joshua Glick · 2023 · Afterimage · 11 citations

    This article explores the rise of deepfake satire as one of the most vibrant subgenres of experimentation within the expanding field of AI art. A combination of “deep learning” and the word “fake,” deepfake videos depict people doing or saying things that they never did or said. While deepfakes have been used to deceive and harm individuals as well as a mass audience, they have also been used toward alternative ends. Deepfake satire offers artful social critique, interrogating the individuals and institutions it portrays as much as the technology used to create it and the platforms on which it circulates. Videos range from snarky jabs at entertainment industry personalities to hard-hitting t

    Save this paper

  6. Enhanced Deepfake Detection Through Multi-Attention Mechanisms: A Comprehensive Framework for Synthetic Media Identification

    Farhan Ali, Zainab Ghazanfar · 2025 · ICCK Transactions on Intelligent Systematics · 8 citations

    The proliferation of deepfake technology poses significant threats to digital media authenticity, necessitating robust detection systems to combat manipulated content. This paper presents a novel attention-based framework for deepfake detection that systematically integrates multiple complementary attention mechanisms to enhance discriminative feature learning. Our approach combines spatial attention, multi-head self-attention, and channel attention modules with a VGG-16 backbone to capture comprehensive representations across different feature spaces. The spatial attention mechanism focuses on discriminative facial regions, while multi-head self-attention captures long-range spatial depende

    Save this paper

  8. Towards Explainable and Robust Deepfake Detection and Attribution: Enhancing Multimedia Forensics for the Next Generation of Synthetic Media

    Raphael Antonius Frick · 2025 · Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security · 1 citations

    The rise of generative AI has enabled the creation of synthetic audio, images, and videos that are virtually indistinguishable from authentic media, presenting new threats to digital trust, privacy, and security. While deepfake detection has advanced, most solutions focus on binary classification performed by data-driven approaches, which are insufficient for attribution and explainability required in high-stakes scenarios. This dissertation aims to develop robust, generalizable, and explainable forensic frameworks that (1) not only detect AI-generated media but also attribute attacks to specific models or methods, (2) provide interpretable evidence for forensic and legal contexts, and (3) a

    Save this paper

  9. Exploring Deepfake Image Forensics: The Role of CNNs, RNNs, GANs and Vision Transformers in Synthetic Media Detection

    Vishal V. D., S. G., B. Sundarambal, et al. · 2025 · 2025 International Conference on Data Science and Business Systems (ICDSBS) · 1 citations

    The advancement of deepfake technology, which is the ability to produce synthetic media of convincingly real likenesses, has created enormous hurdles in the verification and security of digital content. In this light, several deep learning techniques have been employed in identifying deepfake content and lessening its effects. The paper looks at the most recent progress made in deepfake image forensics, especially Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN), and Vision Transformers (ViTs). Models based on these CNN, particularly VGG16, VGG19 and ResNet50, are quite useful in the detection of deepfakes by spatial analysis feature

    Save this paper

  10. Deepfake Detection System Integrating CNN in GAN for Social Media Platforms

    C. Savithri, Manjushree E, J. E, et al. · 2025 · 2025 International Conference on Computing and Communication Technologies (ICCCT) · 1 citations

    Deepfake technology has seen rapid growth which has raised significant concerns regarding privacy, security, and digital trust. Reports from 2023 indicate that over 500,000 deepfake videos and voice manipulations were identified, reflecting a 550% increase since 2019, with fraud cases surging tenfold between 2022 and 2023, emphasizing the urgent need for robust detection mechanisms. This paper introduces a hybrid detection framework that integrates Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) in a parallel processing setup. The CNN component extracts deep features, identifying pixel-level inconsistencies and texture irregularities, while GAN-based adversari

    Save this paper

  11. Deepfake Detection in the Age of Synthetic Media: A Systematic Review

    Satyareddy Ogireddy, Gauri Mathur · 2025 · 2025 International Conference on Networks and Cryptology (NETCRYPT)

    In the current generation social media is the main form of communication for people around the globe. But it is useful in a positive manner. Also, it has some negative impacts such as the spreading of fake news by editing images and videos and sharing them on social media. This is the main area the entire world is looking at because of Artificial intelligence it has become much easier than before to create fake images and videos by using this. This creation of fake images or videos is termed Deepfake. These are the major threats to celebrities and politicians by changing the images and the audio of their videos and by spreading fake news and making people panic. To detect deepfakes many mach

    Save this paper

  12. From Deepfake Detection Research to Public Policy: A Survey on Generalization Challenges in Synthetic Media for the Brazilian Electoral Context

    Thauan de Souza Tavares Da Silva, Diego Addan Gonçalves, David Menotti · 2026 · Journal on Interactive Systems

    Deepfake detection has advanced rapidly in recent years, yet its practical effectiveness remains limited when models are exposed to real-world conditions that differ from controlled benchmarks. This gap is particularly critical in high-stakes scenarios such as electoral processes, where synthetic media can influence public perception at scale. This paper investigates the generalization limitations of current deepfake detection approaches, with emphasis on their applicability in the Brazilian context. Rather than focusing solely on algorithmic performance, we frame deepfake detection as a socio-technical problem, where issues of trust, interpretability, and user response are central to system

    Save this paper

  13. Partial Audio Deepfake Detection: Are We Really Detecting Synthetic Media or Just Dataset Content Biases?

    Arthur Pimentel, Yi Zhu, Tiago H. Falk · 2026 · 2026 IEEE Conference on Artificial Intelligence (CAI)

    In recent years, the generation of highly realistic audio deepfakes has raised significant concerns regarding privacy and information integrity. While most research has focused on fully bonafide or spoofed speech, partial deep-fakes, where only segments of an utterance are manipulated, remain less explored. Given the nature of the task, existing datasets are relying on large language models to manipulate bonafide speech signals into partial deepfakes by altering, deleting, or replacing segments with synthetic content. These manipulations may alter the semantics and sentiment of the generated content, creating biases that can be captured by deepfake detection models, leading to overly optimis

    Save this paper

  14. Beyond Deepfake Detection: MOSAIC, a Confidence-Aware and Counter-Deception Framework for Synthetic-Media Operation Attribution

    Yuval Sinay · 2026 · Proceedings of the 2nd ACM Workshop on Deepfake, Deception, and Disinformation Security

    Synthetic media forensics can detect manipulation and attribute generators, but the operations require a higher-level judgment: whether an artifact can be linked to a coordinated campaign, an operator, or a sponsor. MOSAIC is an integration and decision-control framework with five bounded stages - Media, Origin, Systems, Activity, and Identity - and cross-cutting Confidence and counter-deception controls. An evidence ledger records provenance, quality, diagnosticity, spoof resistance, freshness, dependence, contradictions, and chain of custody; competing hypotheses include false flags, shared tooling, compromised infrastructure, proxies, AI-enabled actor emulation, and unknown actors. Minimu

    Save this paper

  15. Exploration of AI synthetic media and deepfake: understanding the technologies, detection software, legislation, initiatives, and curriculum

    L. Powell, Jr Carl Rebman, H. Wimmer · 2025 · Issues In Information Systems

    Existing research regarding deepfakes has largely concentrated on the technical and legal aspects. As a result, public awareness of deepfakes amongst Americans remains limited. This research employed a qualitative desk/documentary research method to provided comprehensive exploration of the current literature focusing on artificial intelligence (AI)synthetic media with knowledge of the technologies, detection software tools, legislation, organizational initiatives, and higher education resources. It also examined the extent to which deepfake and AI synthetic media content is incorporated into business curricula across 70 AACSB and ACBSP-accredited institutions in Pennsylvania. Specifically,

    Save this paper

  18. Deepfake and Synthetic Media Detection

    Tejas Lokhande, Shreya. D. Ghadge, Janhavi. G. Lakeri, et al. · 2026 · International Research Journal on Advanced Engineering Hub (IRJAEH)

    Deepfake and synthetic media technologies have quickly changed with the growth of artificial intelligence. This has raised serious concerns about misinformation, security, and digital trust. This review paper looks at recent research on deepfake detection in image, video, and audio areas. It studies various methods like Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), MesoNet, and Multilayer Perceptron (MLP) models to see how well they identify manipulated content. The review points out that while existing methods show high accuracy on controlled datasets, they struggle in real-world situations, including issues like compression, noise, and unfamiliar manipulation

    Save this paper

  19. Robust Deepfake Detection via Synthetic Domain Alignment

    Ian Yee, Alan Huang, Shu Hu · 2025 · 2025 IEEE 22nd International Conference on Mobile Ad-Hoc and Smart Systems (MASS)

    Deepfake technology has advanced rapidly in recent years, enabling the creation of hyper-realistic manipulated media that can be weaponized for misinformation, fraud, and identity abuse. While generative models for face swapping and reenactment have improved, deepfake detection models often struggle in real-world deployments due to a multitude of problems. Some of them are due to constant advancements in attacks, domain shifts from generation, and more. This work explores Synthetic Domain Alignment (SDA) as a strategy for improving deepfake detection robustness. SDA leverages an unconditional generative model to synthesize new samples in both the source and target domains, then uses these sy

    Save this paper

  20. FusionNeXt-DF: A Hybrid ConvNeXt-ResNeXt Framework for Robust Deepfake Detection on Cross-Platform Social Media Data

    Swapnil Siddhartha, Pratishtha Verma · 2025 · 2025 IEEE 17th International Conference on Computational Intelligence and Communication Networks (CICN)

    In recent years, the emergence of generative adversarial networks (GANs) and diffusion models has enabled the generation of highly realistic deepfakes, and this has raised critical concerns regarding the credibility, privacy, security, and trust of digital media. When abused, these synthetic manipulations can spread misinformation, damage reputations, and question the authenticity of the online content, which makes it an essential research priority to find reliable identification solutions. Current deepfake detection systems, including CNNbased classifiers, such as Xception, DenseNet, and ResNet, and hybrid CNN- RNN systems, often have difficulty generalizing with new GAN- generated manipula

    Save this paper

  21. Unified Deepfake Detection System for Image, Video and Audio Media

    Neelakantappa T. T., A. J, A. H, et al. · 2025 · International Journal For Multidisciplinary Research

    The rise of deepfake technology poses significant threats to the authenticity of content on social media. This research introduces Sach-AI, a pioneering framework for detecting various deepfakes in video, audio, and image data. Leveraging the power of deep neural networks, Sach-AI utilizes Eulerian Video Magnification combined with the ResNext architecture for enhanced detection. For video deepfakes, Long Short-Term Memory (LSTM) networks are integrated to improve classification tasks. This combination allows Sach-AI to effectively address the evolving, multimodal nature of deepfakes. The framework has been rigorously evaluated using diverse datasets, such as Celeb-DF and FaceForensics , dem

    Save this paper

  23. Deepfake Media Detection Framework Using Machine Learning with Multimodal Feature Extraction for Real and Synthetic Content

    Shraddha Veer, Dr.Sudhir Mohod · 2026 · INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT

    Abstract—The emergence of contemporary deepfakes has at tracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content.Techniques for creating and manipulating multimedia information have progressed to the point where they can now ensure a high degree of realism. DeepFake is a generative deep learning algorithm that creates or modifies face features in a superrealistic form, making it difficult to distinguish between real and fake features. This technology has greatly advanced, promoting a wide range of applications in cinema, such as improv

    Save this paper

Write your paper with these sources

Folio is the integrity-first research workspace: search 200M+ papers, save sources, and write with citations that format themselves. Free for students and researchers.

Start writing free →