Related papers: Breaking Euston: Recovering Private Inputs from Se…

We design a debiased parametric bootstrap framework for statistical inference from differentially private data. Existing usage of the parametric bootstrap on privatized data ignored or avoided handling possible biases introduced by the…

A typical setup in many machine learning scenarios involves a server that holds a model and a user that possesses data, and the challenge is to perform inference while safeguarding the privacy of both parties. Private Inference has been…

Privacy-preserving neural network training in vertically partitioned scenarios is vital for secure collaborative modeling across institutions. This paper presents \textbf{EVA-S2PMLP}, an Efficient, Verifiable, and Accurate Secure Two-Party…

We study information-theoretic security for discrete memoryless interference and broadcast channels with independent confidential messages sent to two receivers. Confidential messages are transmitted to their respective receivers with…

Steganographic protocols enable one to embed covert messages into inconspicuous data over a public communication channel in such a way that no one, aside from the sender and the intended receiver, can even detect the presence of the secret…

A scheme for secure communications, called ``Secret-message Transmission by Echoing Encrypted Probes (STEEP)'', is revisited. STEEP is a round-trip scheme with a probing phase from one user to another and an echoing phase in the reverse…

Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for sensing and computer vision. This approach typically involves a three-stage…

The widespread adoption of outsourced neural network inference presents significant privacy challenges, as sensitive user data is processed on untrusted remote servers. Secure inference offers a privacy-preserving solution, but existing…

Protecting user data privacy can be achieved via many methods, from statistical transformations to generative models. However, all of them have critical drawbacks. For example, creating a transformed data set using traditional techniques is…

This paper considers a multiuser multiple-input single-output (MISO) downlink system with simultaneous wireless information and power transfer. In particular, we focus on secure communication in the presence of passive eavesdroppers and…

Using a broadcast channel to transmit clients' data requests may impose privacy risks. In this paper, we address such privacy concerns in the index coding framework. We show how a malicious client can infer some information about the…

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…

This paper considers a cyber-physical system under an active eavesdropping attack. A remote legitimate user estimates the state of a linear plant from the state information received from a sensor. Transmissions from the sensor occur via an…

In the context of inverse problems $\bf y = Ax$, sparse recovery offers a powerful paradigm shift by enabling the stable solution of ill-posed or underdetermined systems through the exploitation of structure, particularly sparsity. Sparse…

We study the problem of data release with privacy, where data is made available with privacy guarantees while keeping the usability of the data as high as possible --- this is important in health-care and other domains with sensitive data.…

We design short blocklength codes for the Gaussian wiretap channel under information-theoretic security guarantees. Our approach consists in decoupling the reliability and secrecy constraints in our code design. Specifically, we handle the…

We study the problem of remote state estimation in the presence of a passive eavesdropper, under the challenging network environment of no packet receipt acknowledgments. A remote legitimate user estimates the state of a linear plant from…

Deep learning has attracted broad interest in healthcare and medical communities. However, there has been little research into the privacy issues created by deep networks trained for medical applications. Recently developed inference attack…

We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such…

Privacy Preserving Data Mining is a method which ensures privacy of individual information during mining. Most important task involves retrieving information from multiple data bases which is distributed. The data once in the data warehouse…