Related papers: DiffAttack: Diffusion-based Timbre-reserved Advers…
Despite the success of diffusion-based customization methods on visual content creation, increasing concerns have been raised about such techniques from both privacy and political perspectives. To tackle this issue, several…
Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…
We propose DiffSpEx, a generative target speaker extraction method based on score-based generative modelling through stochastic differential equations. DiffSpEx deploys a continuous-time stochastic diffusion process in the complex…
Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…
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…
Diffusion Models (DMs) have achieved remarkable success in realistic voice cloning (VC), while they also increase the risk of malicious misuse. Existing proactive defenses designed for traditional VC models aim to disrupt the forgery…
Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and…
Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…
The widespread use of generative AI has shown remarkable success in producing highly realistic deepfakes, posing a serious threat to various voice biometric applications, including speaker verification, voice biometrics, audio conferencing,…
Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable…
Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed…
Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a more thorough examination of potential security flaws before…
Speaker embedding based zero-shot Text-to-Speech (TTS) systems enable high-quality speech synthesis for unseen speakers using minimal data. However, these systems are vulnerable to adversarial attacks, where an attacker introduces…
Achieving robust generalization against unseen attacks remains a challenge in Audio Deepfake Detection (ADD), driven by the rapid evolution of generative models. To address this, we propose a framework centered on hard sample…
Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. However, we find DiffPure which directly employs the original pre-trained diffusion models for adversarial…
Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…
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…
In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…
This study focuses on the First VoicePrivacy Attacker Challenge within the ICASSP 2025 Signal Processing Grand Challenge, which aims to develop speaker verification systems capable of determining whether two anonymized speech signals are…
Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech…