相关论文: An Effective Energy Mask-based Adversarial Evasion…

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,…

Deep Neural Networks (DNN) are vulnerable to adversarial perturbations-small changes crafted deliberately on the input to mislead the model for wrong predictions. Adversarial attacks have disastrous consequences for deep learning-empowered…

Adversarial attacks hamper the functionality and accuracy of Deep Neural Networks (DNNs) by meddling with subtle perturbations to their inputs.In this work, we propose a new Mask-based Adversarial Defense scheme (MAD) for DNNs to mitigate…

Audio DeepFakes (DF) are artificially generated utterances created using deep learning, with the primary aim of fooling the listeners in a highly convincing manner. Their quality is sufficient to pose a severe threat in terms of security…

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

It is well known that speaker verification systems are subject to spoofing attacks. The Automatic Speaker Verification Spoofing and Countermeasures Challenge -- ASVSpoof2015 -- provides a standard spoofing database, containing attacks based…

Adversarial attacks are inputs that are similar to original inputs but altered on purpose. Speech-to-text neural networks that are widely used today are prone to misclassify adversarial attacks. In this study, first, we investigate the…

Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…

The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions.…

The rapid advancement of speech synthesis and voice conversion technologies has raised significant security concerns in multimedia forensics. Although current detection models demonstrate impressive performance, they struggle to maintain…

Growing interest in automatic speaker verification (ASV)systems has lead to significant quality improvement of spoofing attackson them. Many research works confirm that despite the low equal er-ror rate (EER) ASV systems are still…

Deepfakes utilise Artificial Intelligence (AI) techniques to create synthetic media where the likeness of one person is replaced with another. There are growing concerns that deepfakes can be maliciously used to create misleading and…

Speaker verification systems have been used in many production scenarios in recent years. Unfortunately, they are still highly prone to different kinds of spoofing attacks such as voice conversion and speech synthesis, etc. In this paper,…

In this paper, we present a Small Energy Masking (SEM) algorithm, which masks inputs having values below a certain threshold. More specifically, a time-frequency bin is masked if the filterbank energy in this bin is less than a certain…

Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called…

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these…

Surface electromyography (EMG) enables non-invasive human-computer interaction in rehabilitation, prosthetics, and virtual reality. While deep learning models achieve over 97% classification accuracy, their vulnerability to adversarial…

Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent to a cloud for sound recognition. However, this process may…

Recent work has shown the impact of adversarial machine learning on deep neural networks (DNNs) developed for Radio Frequency Machine Learning (RFML) applications. While these attacks have been shown to be successful in disrupting the…

In recent years, significant progress has been made in deep model-based automatic speech recognition (ASR), leading to its widespread deployment in the real world. At the same time, adversarial attacks against deep ASR systems are highly…