相关论文: SHIELD: A Secure and Highly Enhanced Integrated Le…

The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as…

Machine learning with deep neural networks (DNNs) has become one of the foundation techniques in many safety-critical systems, such as autonomous vehicles and medical diagnosis systems. DNN-based systems, however, are known to be vulnerable…

Spoofed audio, i.e. audio that is manipulated or AI-generated deepfake audio, is difficult to detect when only using acoustic features. Some recent innovative work involving AI-spoofed audio detection models augmented with phonetic and…

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…

The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount…

Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the models from…

Recent advances in audio large language models (ALLMs) have made high-quality synthetic audio widely accessible, increasing the risk of malicious audio deepfakes across speech, environmental sounds, singing voice, and music. Real-world…

The rapid advancement of Generative Artificial Intelligence has fueled deepfake proliferation-synthetic media encompassing fully generated content and subtly edited authentic material-posing challenges to digital security, misinformation…

Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge. The proliferation of speech deepfakes on social media underscores the need…

Recent advancements in generative AI, particularly in speech synthesis, have enabled the generation of highly natural-sounding synthetic speech that closely mimics human voices. While these innovations hold promise for applications like…

Being a form of biometric identification, the security of the speaker identification (SID) system is of utmost importance. To better understand the robustness of SID systems, we aim to perform more realistic attacks in SID, which are…

In real-world applications, it is challenging to build a speaker verification system that is simultaneously robust against common threats, including spoofing attacks, channel mismatch, and domain mismatch. Traditional automatic speaker…

The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data. However, FL is susceptible to backdoor attacks where a small…

Federated learning (FL) is revolutionizing how we learn from data. With its growing popularity, it is now being used in many safety-critical domains such as autonomous vehicles and healthcare. Since thousands of participants can contribute…

The proliferation of audio deepfakes poses a growing threat to trust in digital communications. While detection methods have advanced, attributing audio deepfakes to their source models remains an underexplored yet crucial challenge. In…

Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…

This paper conducts a comprehensive layer-wise analysis of self-supervised learning (SSL) models for audio deepfake detection across diverse contexts, including multilingual datasets (English, Chinese, Spanish), partial, song, and…

With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods. ALM-based deepfake audio currently exhibits widespread, high deception, and type versatility, posing a…

In this study, we propose a timbre-reserved adversarial attack approach for speaker identification (SID) to not only exploit the weakness of the SID model but also preserve the timbre of the target speaker in a black-box attack setting.…

Existing deepfake detection research has primarily focused on scenarios where the manipulated subject is actively speaking, i.e., generating fabricated content by altering the speaker's appearance or voice. However, in realistic interaction…