Related papers: Beyond Identity: A Generalizable Approach for Deep…
Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly received explanation is the tendency of these detectors to…
The advances in generative AI have enabled the creation of synthetic audio which is perceptually indistinguishable from real, genuine audio. Although this stellar progress enables many positive applications, it also raises risks of misuse,…
Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones. This requires robust generalization to new and unseen deepfakes, which emerge frequently, while minimizing…
AI-generated speech is becoming increasingly used in everyday life, powering virtual assistants, accessibility tools, and other applications. However, it is also being exploited for malicious purposes such as impersonation, misinformation,…
Today's generative neural networks allow the creation of high-quality synthetic speech at scale. While we welcome the creative use of this new technology, we must also recognize the risks. As synthetic speech is abused for monetary and…
In the contemporary digital age, the proliferation of deepfakes presents a formidable challenge to the sanctity of information dissemination. Audio deepfakes, in particular, can be deceptively realistic, posing significant risks in…
Due to the rising threat of deepfakes to security and privacy, it is most important to develop robust and reliable detectors. In this paper, we examine the need for high-quality samples in the training datasets of such detectors.…
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…
Current DeepFake detection scenarios are mostly binary, yet data manipulation can vary across audio, video, or both, whose variability is not captured in binary settings. Four-class audio-visual formulations address this by discriminating…
We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt…
This paper proposes an audio-visual deepfake detection approach that aims to capture fine-grained temporal inconsistencies between audio and visual modalities. To achieve this, both architectural and data synthesis strategies are…
The rapid evolution of generative AI has increased the threat of realistic audio-visual deepfakes, demanding robust detection methods. Existing solutions primarily address unimodal (audio or visual) forgeries but struggle with multimodal…
Deepfake detection is a critical task in identifying manipulated multimedia content. In real-world scenarios, deepfake content can manifest across multiple modalities, including audio and video. To address this challenge, we present…
Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse speakers, since generation techniques evolve quickly. Despite…
Adding explanations to audio deepfake detection (ADD) models will boost their real-world application by providing insight on the decision making process. In this paper, we propose a relevancy-based explainable AI (XAI) method to analyze the…
The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality…
Audio deepfakes have improved rapidly recently, yet their effect on human trust in real speech remains unstudied. We present the largest listening study on audio deepfake perception to date, collecting 35,532 judgments from 1,768…
Localizing partial deepfake audio, where only segments of speech are manipulated, remains challenging due to the subtle and scattered nature of these modifications. Existing approaches typically rely on frame-level predictions to identify…
Existing generative models for unsupervised anomalous sound detection are limited by their inability to fully capture the complex feature distribution of normal sounds, while the potential of powerful diffusion models in this domain remains…
Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance, which limits the…