Related papers: VoxGuard: Evaluating User and Attribute Privacy in…
The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its widespread integration across various applications. However, this surge in usage also highlights…
Adolescent suicide is a critical global health issue, and speech provides a cost-effective modality for automatic suicide risk detection. Given the vulnerable population, protecting speaker identity is particularly important, as speech…
Speech synthesis, voice cloning, and voice conversion techniques present severe privacy and security threats to users of voice user interfaces (VUIs). These techniques transform one or more elements of a speech signal, e.g., identity and…
Neural networks are commonly known to be vulnerable to adversarial attacks mounted through subtle perturbation on the input data. Recent development in voice-privacy protection has shown the positive use cases of the same technique to…
Speech is easily leaked imperceptibly, such as being recorded by mobile phones in different situations. Private content in speech may be maliciously extracted through speech enhancement technology. Speech enhancement technology has…
Automatic speech recognition (ASR) systems have been widely deployed in modern smart devices to provide convenient and diverse voice-controlled services. Since ASR systems are vulnerable to audio replay attacks that can spoof and mislead…
Given the increasing privacy concerns from identity theft and the re-identification of speakers through content in the speech field, this paper proposes a prompt-based speech generation pipeline that ensures dual anonymization of both…
Speaker verification (SV) provides billions of voice-enabled devices with access control, and ensures the security of voice-driven technologies. As a type of biometrics, it is necessary that SV is unbiased, with consistent and reliable…
Federated learning has become increasingly widespread due to its ability to train models collaboratively without centralizing sensitive data. While most research on FL emphasizes privacy-preserving techniques during training, the evaluation…
This paper investigates the privacy leakage of smart speakers under an encrypted traffic analysis attack, referred to as voice command fingerprinting. In this attack, an adversary can eavesdrop both outgoing and incoming encrypted voice…
The proliferation of speech technologies and rising privacy legislation calls for the development of privacy preservation solutions for speech applications. These are essential since speech signals convey a wealth of rich, personal and…
Recent advances in machine learning techniques are enabling Automated Speech Recognition (ASR) more accurate and practical. The evidence of this can be seen in the rising number of smart devices with voice processing capabilities. More and…
Children are one of the most under-represented groups in speech technologies, as well as one of the most vulnerable in terms of privacy. Despite this, anonymization techniques targeting this population have received little attention. In…
Machine learning systems can produce personalized outputs that allow an adversary to infer sensitive input attributes at inference time. We introduce Robust Privacy (RP), an inference-time privacy notion inspired by certified robustness: if…
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…
Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges,…
In this paper, we demonstrate that attacks in the latest ASVspoof5 dataset -- a de facto standard in the field of voice authenticity and deepfake detection -- can be identified with surprising accuracy using a small subset of very…
Speaker de-identification aims to conceal a speaker's identity while preserving intelligibility of the underlying speech. We introduce a benchmark that quantifies residual identity leakage with three complementary error rates: equal error…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
Using our voices to access, and interact with, online services raises concerns about the trade-offs between convenience, privacy, and security. The conflict between maintaining privacy and ensuring input authenticity has often been hindered…