Audio plays a crucial role in applications like speaker verification, voice-enabled smart devices, and audio conferencing. However, audio manipulations, such as deepfakes, pose significant risks by enabling the spread of misinformation. Our empirical analysis reveals that existing methods for detecting deepfake audio are often vulnerable to anti-forensic (AF) attacks, particularly those attacked using generative adversarial networks. In this article, we propose a novel collaborative learning method called SHIELD to defend against generative AF attacks. To expose AF signatures, we integrate an auxiliary generative model, called the defense (DF) generative model, which facilitates collaborative learning by combining input and output. Furthermore, we design a triplet model to capture correlations for real and AF attacked audios with real-generated and attacked-generated audios using auxiliary generative models. The proposed SHIELD strengthens the defense against generative AF attacks and achieves robust performance across various generative models. The proposed AF significantly reduces the average detection accuracy from 95.49% to 59.77% for ASVspoof2019, from 99.44% to 38.45% for In-the-Wild, and from 98.41% to 51.18% for HalfTruth for three different generative models. The proposed SHIELD mechanism is robust against AF attacks and achieves an average accuracy of 98.13%, 98.58%, and 99.57% in match, and 98.78%, 98.62%, and 98.85% in mismatch settings for the ASVspoof2019, In-the-Wild, and HalfTruth datasets, respectively.
Recent studies have utilized visual large language models (VLMs) to answer not only "Is this face a forgery?" but also "Why is the face a forgery?" These studies introduced forgery-related attributes, such as forgery location and type, to construct deepfake VQA datasets and train VLMs, achieving high accuracy while providing human-understandable explanatory text descriptions. However, these methods still have limitations. For example, they do not fully leverage face quality-related attributes, which are often abnormal in forged faces, and they lack effective training strategies for forgery-aware VLMs. In this paper, we extend the VQA dataset to create DD-VQA+, which features a richer set of attributes and a more diverse range of samples. Furthermore, we introduce a novel forgery detection framework, MGFFD-VLM, which integrates an Attribute-Driven Hybrid LoRA Strategy to enhance the capabilities of Visual Large Language Models (VLMs). Additionally, our framework incorporates Multi-Granularity Prompt Learning and a Forgery-Aware Training Strategy. By transforming classification and forgery segmentation results into prompts, our method not only improves forgery classification but also enhances interpretability. To further boost detection performance, we design multiple forgery-related auxiliary losses. Experimental results demonstrate that our approach surpasses existing methods in both text-based forgery judgment and analysis, achieving superior accuracy.
Deepfake Technology Unveiled: The Commoditization of AI and Its Impact on Digital Trust. With the increasing accessibility of generative AI, tools for voice cloning, face-swapping, and synthetic media creation have advanced significantly, lowering both financial and technical barriers for their use. While these technologies present innovative opportunities, their rapid growth raises concerns about trust, privacy, and security. This white paper explores the implications of deepfake technology, analyzing its role in enabling fraud, misinformation, and the erosion of authenticity in multimedia. Using cost-effective, easy to use tools such as Runway, Rope, and ElevenLabs, we explore how realistic deepfakes can be created with limited resources, demonstrating the risks posed to individuals and organizations alike. By analyzing the technical and ethical challenges of deepfake mitigation and detection, we emphasize the urgent need for regulatory frameworks, public awareness, and collaborative efforts to maintain trust in digital media.
With the swift progression of image generation technology, the widespread emergence of facial deepfakes poses significant challenges to the field of security, thus amplifying the urgent need for effective deepfake detection.Existing techniques for face forgery detection can broadly be categorized into two primary groups: visual-based methods and multimodal approaches. The former often lacks clear explanations for forgery details, while the latter, which merges visual and linguistic modalities, is more prone to the issue of hallucinations.To address these shortcomings, we introduce a visual detail enhanced self-correction framework, designated CorrDetail, for interpretable face forgery detection. CorrDetail is meticulously designed to rectify authentic forgery details when provided with error-guided questioning, with the aim of fostering the ability to uncover forgery details rather than yielding hallucinated responses. Additionally, to bolster the reliability of its findings, a visual fine-grained detail enhancement module is incorporated, supplying CorrDetail with more precise visual forgery details. Ultimately, a fusion decision strategy is devised to further augment the model's discriminative capacity in handling extreme samples, through the integration of visual information compensation and model bias reduction.Experimental results demonstrate that CorrDetail not only achieves state-of-the-art performance compared to the latest methodologies but also excels in accurately identifying forged details, all while exhibiting robust generalization capabilities.
We introduce a deepfake video detection approach that exploits pixel-wise temporal inconsistencies, which traditional spatial frequency-based detectors often overlook. Traditional detectors represent temporal information merely by stacking spatial frequency spectra across frames, resulting in the failure to detect temporal artifacts in the pixel plane. Our approach performs a 1D Fourier transform on the time axis for each pixel, extracting features highly sensitive to temporal inconsistencies, especially in areas prone to unnatural movements. To precisely locate regions containing the temporal artifacts, we introduce an attention proposal module trained in an end-to-end manner. Additionally, our joint transformer module effectively integrates pixel-wise temporal frequency features with spatio-temporal context features, expanding the range of detectable forgery artifacts. Our framework represents a significant advancement in deepfake video detection, providing robust performance across diverse and challenging detection scenarios.
Recent advances in AIGC have exacerbated the misuse of malicious deepfake content, making the development of reliable deepfake detection methods an essential means to address this challenge. Although existing deepfake detection models demonstrate outstanding performance in detection metrics, most methods only provide simple binary classification results, lacking interpretability. In critical domains such as law, interpretability is crucial for enhancing the credibility and authority of decisions. Recent studies attempt to improve the interpretability of classification results by providing spatial manipulation masks or temporal forgery segments. However, the practical effectiveness of these methods remains suboptimal due to limitations of the forgery data. Most current deepfake datasets predominantly offer binary labels, only a few datasets with localization annotations. However, they suffer from restricted forgery scenarios, limited diversity in deepfake types, and insufficient data scale, making them inadequate for complex real-world scenarios. To address this predicament, we construct a novel large-scale deepfake detection and localization ($\textbf{DDL}$) dataset containing over $\textbf{1.8M}$ forged samples and encompassing up to $\textbf{75}$ distinct deepfake methods. The DDL design incorporates four key innovations: (1) $\textbf{Diverse Forgery Scenarios}$, (2) $\textbf{Comprehensive Deepfake Methods}$, (3) $\textbf{Varied Manipulation Modes}$, and (4) $\textbf{Fine-grained Forgery Annotations}$. Through these improvements, our DDL not only provides a more challenging benchmark for complex real-world forgeries, but also offers crucial support for building next-generation deepfake detection, localization, and interpretability methods. The DDL dataset project page is on https://deepfake-workshop-ijcai2025.github.io/main/index.html.
We introduce a post-training approach that adapts self-supervised learning (SSL) models for deepfake speech detection by bridging the gap between general pre-training and domain-specific fine-tuning. We present AntiDeepfake models, a series of post-trained models developed using a large-scale multilingual speech dataset containing over 56,000 hours of genuine speech and 18,000 hours of speech with various artifacts in over one hundred languages. Experimental results show that the post-trained models already exhibit strong robustness and generalization to unseen deepfake speech. When they are further fine-tuned on the Deepfake-Eval-2024 dataset, these models consistently surpass existing state-of-the-art detectors that do not leverage post-training. Model checkpoints and source code are available online.
Advancements in audio deepfake technology offers benefits like AI assistants, better accessibility for speech impairments, and enhanced entertainment. However, it also poses significant risks to security, privacy, and trust in digital communications. Detecting and mitigating these threats requires comprehensive datasets. Existing datasets lack diverse ethnic accents, making them inadequate for many real-world scenarios. Consequently, models trained on these datasets struggle to detect audio deepfakes in diverse linguistic and cultural contexts such as in South-Asian countries. Ironically, there is a stark lack of South-Asian speaker samples in the existing datasets despite constituting a quarter of the worlds population. This work introduces the IndieFake Dataset (IFD), featuring 27.17 hours of bonafide and deepfake audio from 50 English speaking Indian speakers. IFD offers balanced data distribution and includes speaker-level characterization, absent in datasets like ASVspoof21 (DF). We evaluated various baselines on IFD against existing ASVspoof21 (DF) and In-The-Wild (ITW) datasets. IFD outperforms ASVspoof21 (DF) and proves to be more challenging compared to benchmark ITW dataset. The complete dataset, along with documentation and sample reference clips, is publicly accessible for research use on project website.
Face swapping manipulations in video streams represents an increasing threat in remote video communications, due to advances in automated and real-time tools. Recent literature proposes to characterize and exploit visual artifacts introduced in video frames by swapping algorithms when dealing with challenging physical scenes, such as face occlusions. This paper investigates the effectiveness of this approach by benchmarking CNN-based data-driven models on two data corpora (including a newly collected one) and analyzing generalization capabilities with respect to different acquisition sources and swapping algorithms. The results confirm excellent performance of general-purpose CNN architectures when operating within the same data source, but a significant difficulty in robustly characterizing occlusion-based visual cues across datasets. This highlights the need for specialized detection strategies to deal with such artifacts.
Face identity provides a powerful signal for deepfake detection. Prior studies show that even when not explicitly modeled, classifiers often learn identity features implicitly. This has led to conflicting views: some suppress identity cues to reduce bias, while others rely on them as forensic evidence. To reconcile these views, we analyze two hypotheses: (1) whether face identity alone is discriminative for detecting deepfakes, and (2) whether such identity features generalize poorly across manipulation methods. Our experiments confirm that identity is informative but context-dependent. While some manipulations preserve identity-consistent artifacts, others distort identity cues and harm generalization. We argue that identity features should neither be blindly suppressed nor relied upon, but instead be explicitly modeled and adaptively controlled based on per-sample relevance. We propose \textbf{SELFI} (\textbf{SEL}ective \textbf{F}usion of \textbf{I}dentity), a generalizable detection framework that dynamically modulates identity usage. SELFI consists of: (1) a Forgery-Aware Identity Adapter (FAIA) that extracts identity embeddings from a frozen face recognition model and projects them into a forgery-relevant space via auxiliary supervision; and (2) an Identity-Aware Fusion Module (IAFM) that selectively integrates identity and visual features using a relevance-guided fusion mechanism. Experiments on four benchmarks show that SELFI improves cross-manipulation generalization, outperforming prior methods by an average of 3.1\% AUC. On the challenging DFDC dataset, SELFI exceeds the previous best by 6\%. Code will be released upon paper acceptance.
The rapid evolution of image generation models has revolutionized visual content creation, enabling the synthesis of highly realistic and contextually accurate images for diverse applications. However, the potential for misuse, such as deepfake generation, image based phishing attacks, and fabrication of misleading visual evidence, underscores the need for robust authenticity verification mechanisms. While traditional statistical watermarking techniques have proven effective for autoregressive language models, their direct adaptation to image generation models encounters significant challenges due to a phenomenon we term retokenization mismatch, a disparity between original and retokenized sequences during the image generation process. To overcome this limitation, we propose C-reweight, a novel, distortion-free watermarking method explicitly designed for image generation models. By leveraging a clustering-based strategy that treats tokens within the same cluster equivalently, C-reweight mitigates retokenization mismatch while preserving image fidelity. Extensive evaluations on leading image generation platforms reveal that C-reweight not only maintains the visual quality of generated images but also improves detectability over existing distortion-free watermarking techniques, setting a new standard for secure and trustworthy image synthesis.
With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.
Generalization remains a critical challenge in speech deepfake detection (SDD). While various approaches aim to improve robustness, generalization is typically assessed through performance metrics like equal error rate without a theoretical framework to explain model performance. This work investigates sharpness as a theoretical proxy for generalization in SDD. We analyze how sharpness responds to domain shifts and find it increases in unseen conditions, indicating higher model sensitivity. Based on this, we apply Sharpness-Aware Minimization (SAM) to reduce sharpness explicitly, leading to better and more stable performance across diverse unseen test sets. Furthermore, correlation analysis confirms a statistically significant relationship between sharpness and generalization in most test settings. These findings suggest that sharpness can serve as a theoretical indicator for generalization in SDD and that sharpness-aware training offers a promising strategy for improving robustness.
The widespread emergence of face-swap Deepfake videos poses growing risks to digital security, privacy, and media integrity, necessitating effective forensic tools for identifying the source of such manipulations. Although most prior research has focused primarily on binary Deepfake detection, the task of model attribution -- determining which generative model produced a given Deepfake -- remains underexplored. In this paper, we introduce FAME (Fake Attribution via Multilevel Embeddings), a lightweight and efficient spatio-temporal framework designed to capture subtle generative artifacts specific to different face-swap models. FAME integrates spatial and temporal attention mechanisms to improve attribution accuracy while remaining computationally efficient. We evaluate our model on three challenging and diverse datasets: Deepfake Detection and Manipulation (DFDM), FaceForensics++, and FakeAVCeleb. Results show that FAME consistently outperforms existing methods in both accuracy and runtime, highlighting its potential for deployment in real-world forensic and information security applications.
Evaluating explainability techniques, such as SHAP and LRP, in the context of audio deepfake detection is challenging due to lack of clear ground truth annotations. In the cases when we are able to obtain the ground truth, we find that these methods struggle to provide accurate explanations. In this work, we propose a novel data-driven approach to identify artifact regions in deepfake audio. We consider paired real and vocoded audio, and use the difference in time-frequency representation as the ground-truth explanation. The difference signal then serves as a supervision to train a diffusion model to expose the deepfake artifacts in a given vocoded audio. Experimental results on the VocV4 and LibriSeVoc datasets demonstrate that our method outperforms traditional explainability techniques, both qualitatively and quantitatively.
Deepfake detection has gained significant attention across audio, text, and image modalities, with high accuracy in distinguishing real from fake. However, identifying the exact source--such as the system or model behind a deepfake--remains a less studied problem. In this paper, we take a significant step forward in audio deepfake model attribution or source tracing by proposing a training-free, green AI approach based entirely on k-Nearest Neighbors (kNN). Leveraging a pre-trained self-supervised learning (SSL) model, we show that grouping samples from the same generator is straightforward--we obtain an 0.93 F1-score across five deepfake datasets. The method also demonstrates strong out-of-domain (OOD) detection, effectively identifying samples from unseen models at an F1-score of 0.84. We further analyse these results in a multi-dimensional approach and provide additional insights. All code and data protocols used in this work are available in our open repository: https://github.com/adrianastan/tada/.
Deepfakes are AI-synthesized multimedia data that may be abused for spreading misinformation. Deepfake generation involves both visual and audio manipulation. To detect audio-visual deepfakes, previous studies commonly employ two relatively independent sub-models to learn audio and visual features, respectively, and fuse them subsequently for deepfake detection. However, this may underutilize the inherent correlations between audio and visual features. Moreover, utilizing two isolated feature learning sub-models can result in redundant neural layers, making the overall model inefficient and impractical for resource-constrained environments. In this work, we design a lightweight network for audio-visual deepfake detection via a single-stream multi-modal learning framework. Specifically, we introduce a collaborative audio-visual learning block to efficiently integrate multi-modal information while learning the visual and audio features. By iteratively employing this block, our single-stream network achieves a continuous fusion of multi-modal features across its layers. Thus, our network efficiently captures visual and audio features without the need for excessive block stacking, resulting in a lightweight network design. Furthermore, we propose a multi-modal classification module that can boost the dependence of the visual and audio classifiers on modality content. It also enhances the whole resistance of the video classifier against the mismatches between audio and visual modalities. We conduct experiments on the DF-TIMIT, FakeAVCeleb, and DFDC benchmark datasets. Compared to state-of-the-art audio-visual joint detection methods, our method is significantly lightweight with only 0.48M parameters, yet it achieves superiority in both uni-modal and multi-modal deepfakes, as well as in unseen types of deepfakes.
Generative AI advances rapidly, allowing the creation of very realistic manipulated video and audio. This progress presents a significant security and ethical threat, as malicious users can exploit DeepFake techniques to spread misinformation. Recent DeepFake detection approaches explore the multimodal (audio-video) threat scenario. In particular, there is a lack of reproducibility and critical issues with existing datasets - such as the recently uncovered silence shortcut in the widely used FakeAVCeleb dataset. Considering the importance of this topic, we aim to gain a deeper understanding of the key issues affecting benchmarking in audio-video DeepFake detection. We examine these challenges through the lens of the three core benchmarking pillars: datasets, detection methods, and evaluation protocols. To address these issues, we spotlight the recent DeepSpeak v1 dataset and are the first to propose an evaluation protocol and benchmark it using SOTA models. We introduce SImple Multimodal BAseline (SIMBA), a competitive yet minimalistic approach that enables the exploration of diverse design choices. We also deepen insights into the issue of audio shortcuts and present a promising mitigation strategy. Finally, we analyze and enhance the evaluation scheme on the widely used FakeAVCeleb dataset. Our findings offer a way forward in the complex area of audio-video DeepFake detection.
The rapid advancement of deep generative models has significantly improved the realism of synthetic media, presenting both opportunities and security challenges. While deepfake technology has valuable applications in entertainment and accessibility, it has emerged as a potent vector for misinformation campaigns, particularly on social media. Existing detection frameworks struggle to distinguish between benign and adversarially generated deepfakes engineered to manipulate public perception. To address this challenge, we introduce SocialDF, a curated dataset reflecting real-world deepfake challenges on social media platforms. This dataset encompasses high-fidelity deepfakes sourced from various online ecosystems, ensuring broad coverage of manipulative techniques. We propose a novel LLM-based multi-factor detection approach that combines facial recognition, automated speech transcription, and a multi-agent LLM pipeline to cross-verify audio-visual cues. Our methodology emphasizes robust, multi-modal verification techniques that incorporate linguistic, behavioral, and contextual analysis to effectively discern synthetic media from authentic content.
The growing prevalence of real-world deepfakes presents a critical challenge for existing detection systems, which are often evaluated on datasets collected just for scientific purposes. To address this gap, we introduce a novel dataset of real-world audio deepfakes. Our analysis reveals that these real-world examples pose significant challenges, even for the most performant detection models. Rather than increasing model complexity or exhaustively search for a better alternative, in this work we focus on a data-centric paradigm, employing strategies like dataset curation, pruning, and augmentation to improve model robustness and generalization. Through these methods, we achieve a 55% relative reduction in EER on the In-the-Wild dataset, reaching an absolute EER of 1.7%, and a 63% reduction on our newly proposed real-world deepfakes dataset, AI4T. These results highlight the transformative potential of data-centric approaches in enhancing deepfake detection for real-world applications. Code and data available at: https://github.com/davidcombei/AI4T.