Related papers: Towards Anonymous Neural Network Inference
Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative intent and obscure necessary information. This is…
In this paper, we introduce a novel approach to neural learning: the Feature-Imitating-Network (FIN). A FIN is a neural network with weights that are initialized to reliably approximate one or more closed-form statistical features, such as…
Machine learning has become a critical component of modern data-driven online services. Typically, the training phase of machine learning techniques requires to process large-scale datasets which may contain private and sensitive…
Federated Learning enables diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Despite existing privacy measures, concerns arise from potential…
Real-time sequence identification is a core use-case of artificial neural networks (ANNs), ranging from recognizing temporal events to identifying verification codes. Existing methods apply recurrent neural networks, which suffer from…
In this paper we address the issue of identity and access control within shared permissioned blockchains. We propose the ChainAchor system that provides anonymous but verifiable identities for entities on the blockchain. ChainAchor also…
Fully homomorphic encryption (FHE) is a promising cryptographic primitive for realizing private neural network inference (PI) services by allowing a client to fully offload the inference task to a cloud server while keeping the client data…
Simply restricting the computation to non-sensitive part of the data may lead to inferences on sensitive data through data dependencies. Inference control from data dependencies has been studied in the prior work. However, existing…
The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial…
We propose a novel artificial noise (AN) injection scheme for wireless systems over quasi-static fading channels, in which a single-antenna transmitter sends confidential messages to a half-duplex receiver in the presence of an…
This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the sensor data have different underlying…
We provide enhanced security against insider attacks in services that manage extremely sensitive data. One example is a #MeToo use case where sexual harassment complaints are reported but only revealed when another complaint is filed…
Collaborative inference in next-generation networks can enhance Artificial Intelligence (AI) applications, including autonomous driving, personal identification, and activity classification. This method involves a three-stage process: a)…
This paper presents a private transfer architecture for the Internet Computer (ICP) that decouples deposit and retrieval through two short-lived intermediaries, with sealed storage and attested teardown by an ephemeral witness. The protocol…
In this dissertation project, we describe and implement a practical system application based on a selective disclosure credential scheme, namely the Coconut credential scheme\cite{sonnino_coconut:_2018}. The specific application here is an…
The right to be forgotten is a fundamental principle of privacy-preserving regulations and extends to Machine Learning (ML) paradigms such as Federated Learning (FL). While FL enhances privacy by enabling collaborative model training…
High availability is no longer just a business continuity concern. Users are increasingly dependant on devices that consume and produce data in ever increasing volumes. A popular solution is to have a central repository which each device…
The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted…
We address the challenge of preserving emotional content in streaming speaker anonymization (SA). Neural audio codec language models trained for audio continuation tend to degrade source emotion: content tokens discard emotional…
Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections) and diverse, high-resolution inputs. Modern text-to-image…