相关论文: MIS-AVoiDD: Modality Invariant and Specific Repres…
Previous deepfake detection methods mostly depend on low-level textural features vulnerable to perturbations and fall short of detecting unseen forgery methods. In contrast, high-level semantic features are less susceptible to perturbations…
Speech deepfakes pose a significant threat to personal security and content authenticity. Several detectors have been proposed in the literature, and one of the primary challenges these systems have to face is the generalization over unseen…
The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio deepfakes. A recent technique, FOICE [USENIX'24], demonstrates a particularly alarming capability:…
Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes" has emerged. This research most often focuses on the image domain, while…
Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipulation methods. To address this, we propose a novel…
The growing sophistication of speech generated by Artificial Intelligence (AI) has introduced new challenges in audio deepfake detection. Text-to-speech (TTS) and voice conversion (VC) technologies can create highly convincing synthetic…
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…
The detection and localization of deepfake content, particularly when small fake segments are seamlessly mixed with real videos, remains a significant challenge in the field of digital media security. Based on the recently released…
Sound event localization and detection (SELD) combines two subtasks: sound event detection (SED) and direction of arrival (DOA) estimation. SELD is usually tackled as an audio-only problem, but visual information has been recently included.…
Voice spoofing attacks pose a significant threat to automated speaker verification systems. Existing anti-spoofing methods often simulate specific attack types, such as synthetic or replay attacks. However, in real-world scenarios, the…
Multi-modal emotion recognition in conversations is a challenging problem due to the complex and complementary interactions between different modalities. Audio and textual cues are particularly important for understanding emotions from a…
As speech generation technology advances, the risk of misuse through deepfake audio has become a pressing concern, which underscores the critical need for robust detection systems. However, many existing speech deepfake datasets are limited…
The rapid advancement of generative adversarial networks (GANs) and diffusion models has enabled the creation of highly realistic deepfake content, posing significant threats to digital trust across audio-visual domains. While unimodal…
Following the recent initiatives for the democratization of AI, deep fake generators have become increasingly popular and accessible, causing dystopian scenarios towards social erosion of trust. A particular domain, such as biological…
This perspective calls for scholars across disciplines to address the challenge of audio deepfake detection and discernment through an interdisciplinary lens across Artificial Intelligence methods and linguistics. With an avalanche of tools…
With the advancement of audio generation, generative models can produce highly realistic audios. However, the proliferation of deepfake general audio can pose negative consequences. Therefore, we propose a new task, deepfake general audio…
Anomaly synthesis is one of the effective methods to augment abnormal samples for training. However, current anomaly synthesis methods predominantly rely on texture information as input, which limits the fidelity of synthesized abnormal…
The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without additional training. In current AV-LLMs, audio and video features are typically…
Unmanned aerial vehicle (UAV) detection and aerial object recognition are critical for modern surveillance and security, prompting a need for robust systems that overcome limitations of single-modality approaches. This research addresses…
This paper describes the deepfake audio detection system submitted to the Audio Deep Synthesis Detection (ADD) Challenge Track 3.2 and gives an analysis of score fusion. The proposed system is a score-level fusion of several light…