相关论文: CloneShield: A Framework for Universal Perturbatio…

Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like…

In this paper, we propose MelShield, a robust, in-generation, keyed audio watermarking framework that embeds identifiable signals into AI-generated audio for copyright protection and reliable attribution. Specifically, MelShield operates in…

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

While neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible for the vast majority of the world's…

Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity preservation is important, such as completing a recording, dubbing in a new language, or preserving the…

Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on…

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech…

Audio watermarking has been widely applied in copyright protection and source tracing. However, due to the inherent characteristics of audio signals, watermark localization and resistance to desynchronization attacks remain significant…

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires…

Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice…

Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, malicious exploitation like voice-cloning fraud poses severe…

Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Although adversarial perturbations offer a potential defense,…

Synthetic-voice cloning technologies have seen significant advances in recent years, giving rise to a range of potential harms. From small- and large-scale financial fraud to disinformation campaigns, the need for reliable methods to…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

With the rapid progress in diffusion models, image synthesis has advanced to the stage of zero-shot image-to-image generation, where high-fidelity replication of facial identities or artistic styles can be achieved using just one portrait…

In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single…

Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for…

Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently, by using a well-trained source TTS model without adapting it on the speech data of new speakers. Considering seen and unseen speakers have diverse…

We present CallShield, the first caller identity authentication system that operates entirely at the audio layer, without relying on speech transcription, internet connectivity, or trusted infrastructure. CallShield introduces a real-time…