相关论文: Guiding Text-to-Text Privatization by Syntax

We introduce a framework that recommends music based on the emotions of speech. In content creation and daily life, speech contains information about human emotions, which can be enhanced by music. Our framework focuses on a cross-domain…

The problem of privately releasing data is to provide a version of a dataset without revealing sensitive information about the individuals who contribute to the data. The model of differential privacy allows such private release while…

Metric Differential Privacy (mDP) extends the concept of Differential Privacy (DP) to serve as a new paradigm of data perturbation. It is designed to protect secret data represented in general metric space, such as text data encoded as word…

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our…

Neural machine translation (NMT) is notoriously sensitive to noises, but noises are almost inevitable in practice. One special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations. We…

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Differential privacy is a widely adopted framework designed to safeguard the sensitive information of data providers within a data set. It is based on the application of controlled noise at the interface between the server that stores and…

Word embeddings are usually derived from corpora containing text from many individuals, thus leading to general purpose representations rather than individually personalized representations. While personalized embeddings can be useful to…

Existing privacy-preserving speech representation learning methods target a single application domain. In this paper, we present a novel framework to anonymize utterance-level speech embeddings generated by pre-trained encoders and show its…

Text-to-speech systems recently achieved almost indistinguishable quality from human speech. However, the prosody of those systems is generally flatter than natural speech, producing samples with low expressiveness. Disentanglement of…

Personalizing large-scale diffusion models poses serious privacy risks, especially when adapting to small, sensitive datasets. A common approach is to fine-tune the model using differentially private stochastic gradient descent (DP-SGD),…

Most text-to-image customization techniques fine-tune models on a small set of \emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to…

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and…

Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel…

Recordings in everyday life require privacy preservation of the speech content and speaker identity. This contribution explores the influence of noise and reverberation on the trade-off between privacy and utility for low-cost…

Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictions. Recently, it was proposed that this behavior can be…