Related papers: Understanding the Tradeoffs in Client-side Privacy…

Cloud computing enables users to process and store data remotely on high-performance computers and servers by sharing data over the Internet. However, transferring data to clouds causes unavoidable privacy concerns. Here, we present a…

The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query. The lack of…

We consider the critical problem of distributed learning over data while keeping it private from the computational servers. The state-of-the-art approaches to this problem rely on quantizing the data into a finite field, so that the…

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…

This paper describes the implementation of a system to recognize employees and visitors wanting to gain access to a physical office through face images and speech-to-text recognition. The system helps employees to unlock the entrance door…

Nowadays, more and more machine learning applications, such as medical diagnosis, online fraud detection, email spam filtering, etc., services are provided by cloud computing. The cloud service provider collects the data from the various…

Smart devices serviced by large-scale AI models necessitates user data transfer to the cloud for inference. For speech applications, this means transferring private user information, e.g., speaker identity. Our paper proposes a…

The extensive use of online social media has highlighted the importance of privacy in the digital space. As more scientists analyse the data created in these platforms, privacy concerns have extended to data usage within the academia.…

Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality…

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…

As image processing systems proliferate, privacy concerns intensify given the sensitive personal information contained in images. This paper examines privacy challenges in image processing and surveys emerging privacy-preserving techniques…

Speech data is expensive to collect, and incredibly sensitive to its sources. It is often the case that organizations independently collect small datasets for their own use, but often these are not performant for the demands of machine…

The integration of fairness and privacy in centralized data-driven applications is critical, especially as these systems increasingly influence sectors with significant societal impact. Current methods rarely address privacy, fairness, and…

Audio is an important medium in people's daily life, hidden information can be embedded into audio for covert communication. Current audio information hiding techniques can be roughly classed into time domain-based and transform…

Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a great number of…

Privacy policies are the main way to obtain information related to personal data collection and processing. Originally, privacy policies were presented as textual documents. However, the unsuitability of this format for the needs of today's…

Differential privacy has become the gold standard for privacy-preserving machine learning systems. Unfortunately, subsequent work has primarily fixated on the privacy-utility tradeoff, leaving the subject of fairness constraints undervalued…

The performance of a voice anonymization system is typically measured according to its ability to hide the speaker's identity and keep the data's utility for downstream tasks. This means that the requirements the anonymization should…

This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data…