相关论文: WaveFuzz: A Clean-Label Poisoning Attack to Protec…

Automatic speaker verification (ASV) systems utilize the biometric information in human speech to verify the speaker's identity. The techniques used for performing speaker verification are often vulnerable to malicious attacks that attempt…

Federated Learning (FL) is a machine learning (ML) approach that enables multiple decentralized devices or edge servers to collaboratively train a shared model without exchanging raw data. During the training and sharing of model updates…

Language models have shown promise in various tasks but can be affected by undesired data during training, fine-tuning, or alignment. For example, if some unsafe conversations are wrongly annotated as safe ones, the model fine-tuned on…

With a recent influx of voice generation methods, the threat introduced by audio DeepFake (DF) is ever-increasing. Several different detection methods have been presented as a countermeasure. Many methods are based on so-called front-ends,…

This demo paper examines the susceptibility of Federated Learning (FL) systems to targeted data poisoning attacks, presenting a novel system for visualizing and mitigating such threats. We simulate targeted data poisoning attacks via label…

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals.…

Advancements in artificial intelligence and machine learning have significantly improved synthetic speech generation. This paper explores diffusion models, a novel method for creating realistic synthetic speech. We create a diffusion…

Voice anti-spoofing aims at classifying a given utterance either as a bonafide human sample, or a spoofing attack (e.g. synthetic or replayed sample). Many anti-spoofing methods have been proposed but most of them fail to generalize across…

Speech deepfakes are artificial voices generated by machine learning models. Previous literature has highlighted deepfakes as one of the biggest security threats arising from progress in artificial intelligence due to their potential for…

Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015…

Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in neural and digital signal processing-based watermarking methods have…

Audio DeepFakes allow the creation of high-quality, convincing utterances and therefore pose a threat due to its potential applications such as impersonation or fake news. Methods for detecting these manipulations should be characterized by…

The rapid advancement of speech synthesis technologies, including text-to-speech (TTS) and voice conversion (VC), has intensified security and privacy concerns related to voice cloning. Recent defenses attempt to prevent unauthorized…

Federated Learning (FL), as a popular distributed learning paradigm, has shown outstanding performance in improving computational efficiency and protecting data privacy, and is widely applied in industrial image classification. However, due…

Component-level audio Spoofing (Comp-Spoof) targets a new form of audio manipulation where only specific components of a signal, such as speech or environmental sound, are forged or substituted while other components remain genuine.…

Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based…

All existing databases of spoofed speech contain attack data that is spoofed in its entirety. In practice, it is entirely plausible that successful attacks can be mounted with utterances that are only partially spoofed. By definition,…

The deep learning models used for speaker verification rely heavily on large amounts of data and correct labeling. However, noisy (incorrect) labels often occur, which degrades the performance of the system. In this paper, we propose a…

Evasion attacks pose significant threats to AI systems, exploiting vulnerabilities in machine learning models to bypass detection mechanisms. The widespread use of voice data, including deepfakes, in promising future industries is currently…