Related papers: Anonymizing Sensor Data on the Edge: A Representat…

Distributed devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the…

Noting the importance of the latent variables in inference and learning, we propose a novel framework for autoencoders based on the homeomorphic transformation of latent variables, which could reduce the distance between vectors in the…

Many mobile applications and virtual conversational agents now aim to recognize and adapt to emotions. To enable this, data are transmitted from users' devices and stored on central servers. Yet, these data contain sensitive information…

Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by these embeddings lends them versatility, but also raises…

In an Internet of Things network, multiple sensors send information to a fusion center for it to infer a public hypothesis of interest. However, the same sensor information may be used by the fusion center to make inferences of a private…

Privacy and security are major concerns when communicating speech signals to cloud services such as automatic speech recognition (ASR) and speech emotion recognition (SER). Existing solutions for speech anonymization mainly focus on voice…

The remarkable success of machine learning, especially deep learning, has produced a variety of cloud-based services for mobile users. Such services require an end user to send data to the service provider, which presents a serious…

Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the…

Privacy of machine learning models is one of the remaining challenges that hinder the broad adoption of Artificial Intelligent (AI). This paper considers this problem in the context of image datasets containing faces. Anonymization of such…

With the emergence of smart cities, Internet of Things (IoT) devices as well as deep learning technologies have witnessed an increasing adoption. To support the requirements of such paradigm in terms of memory and computation, joint and…

The use of AI in public spaces continually raises concerns about privacy and the protection of sensitive data. An example is the deployment of detection and recognition methods on humans, where images are provided by surveillance cameras.…

Data living on manifolds commonly appear in many applications. Often this results from an inherently latent low-dimensional system being observed through higher dimensional measurements. We show that under certain conditions, it is possible…

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…

The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a…

Latent diffusion models can be used as a powerful augmentation method to artificially extend datasets for enhanced training. To the human eye, these augmented images look very different to the originals. Previous work has suggested to use…

Embedded systems demand on-device processing of data using Neural Networks (NNs) while conforming to the memory, power and computation constraints, leading to an efficiency and accuracy tradeoff. To bring NNs to edge devices, several…

Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this…

We present a privacy-enhancing mechanism for gaze signals using a latent-noise autoencoder that prevents users from being re-identified across play sessions without their consent, while retaining the usability of the data for benign tasks.…

The Internet of Things (IoT) presents a unique cybersecurity challenge due to its vast network of interconnected, resource-constrained devices. These vulnerabilities not only threaten data integrity but also the overall functionality of IoT…

Motivation: Human genomic datasets often contain sensitive information that limits use and sharing of the data. In particular, simple anonymisation strategies fail to provide sufficient level of protection for genomic data, because the data…