相关论文: A Tandem Framework Balancing Privacy and Security …

Credential theft and remote attacks are the most serious threats to user authentication mechanisms. The crux of these problems is that we cannot control such behaviors. However, if a password does not contain user secrets, stealing it is…

A general disentanglement-based speaker anonymization system typically separates speech into content, speaker, and prosody features using individual encoders. This paper explores how to adapt such a system when a new speech attribute, for…

Significant advancements made in the generation of deepfakes have caused security and privacy issues. Attackers can easily impersonate a person's identity in an image by replacing his face with the target person's face. Moreover, a new…

Facilitated by the speech generation framework that disentangles speech into content, speaker, and prosody, voice anonymization is accomplished by substituting the original speaker embedding vector with that of a pseudo-speaker. In this…

Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further…

Mobile Graphical User Interface (GUI) agents have demonstrated strong capabilities in automating complex smartphone tasks by leveraging multimodal large language models (MLLMs) and system-level control interfaces. However, this paradigm…

The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and…

Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymization. In this paper, we propose a novel anonymization framework…

Voice impersonation is not the same as voice transformation, although the latter is an essential element of it. In voice impersonation, the resultant voice must convincingly convey the impression of having been naturally produced by the…

As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awareness in physical environments becomes critical. Unlike digital chatbots, these agents operate in…

As generative AI (GenAI) systems become increasingly prevalent across various technological stacks, the question of how such systems handle sensitive and personal data flows becomes increasingly important. Specifically, both the ability to…

The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker selection technique as a baseline for the first VoicePrivacy…

Motivated by an increasing need for privacy-preserving voice communications, we investigate here the original idea of sending encrypted data and speech in the form of pseudo-speech signals in the audio domain. Being less constrained than…

In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and…

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting.…

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…

Speech pseudonymization aims at altering a speech signal to map the identifiable personal characteristics of a given speaker to another identity. In other words, it aims to hide the source speaker identity while preserving the…

We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice…

Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity. This paper proposes an effective and parameter-efficient speaker…

In order to protect the privacy of speech data, speaker anonymization aims for hiding the identity of a speaker by changing the voice in speech recordings. This typically comes with a privacy-utility trade-off between protection of…