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

The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing…

This paper investigates the fundamental performance limits of the two-user interference channel in the presence of an external eavesdropper. In this setting, we construct an inner bound, to the secrecy capacity region, based on the idea of…

Growing concern for individual privacy, driven by an increased public awareness of the degree to which many of our electronic activities are tracked by interested third parties (e.g. Google knows what I am thinking before I finish entering…

State-of-the-art important passage retrieval methods obtain very good results, but do not take into account privacy issues. In this paper, we present a privacy preserving method that relies on creating secure representations of documents.…

In this paper, we consider a scenario where a source node wishes to broadcast two confidential messages for two respective receivers, while a wire-tapper also receives the transmitted signal. This model is motivated by wireless…

Remotely generated data by Intent of Things (IoT) has recently had a lot of attention for their huge benefits such as efficient monitoring and risk reduction. The transmitted streams usually consist of periodical streams (e.g. activities)…

We introduce a method for securely delivering a set of messages to a group of clients over a broadcast erasure channel where each client is interested in a distinct message. Each client is able to obtain its own message but not the others'.…

We propose a novel method for privacy-preserving fine-tuning vision transformers (ViTs) with encrypted images. Conventional methods using encrypted images degrade model performance compared with that of using plain images due to the…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…

Data mining has made broad significant multidisciplinary field used in vast application domains and extracts knowledge by identifying structural relationship among the objects in large data bases. Privacy preserving data mining is a new…

Electronic devices and cables inadvertently emit RF emissions as a byproduct of signal processing and/or transmission. Labeled as electromagnetic emanations, they form an EM side-channel for data leakage. Previously, it was believed that…

In this paper, we present a stealthy and effective attack that exposes privacy vulnerabilities in Graph Neural Networks (GNNs) by inferring private links within graph-structured data. Focusing on the inductive setting where new nodes join…

The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the…

Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis. However, their use in Machine Learning as a Service (MLaaS) raises significant privacy concerns, as centralized servers process…

In this paper, we consider a scenario where a source node wishes to broadcast two confidential messages to two receivers, while a wire-tapper also receives the transmitted signal. This model is motivated by wireless communications, where…

Differential privacy guarantees allow the results of a statistical analysis involving sensitive data to be released without compromising the privacy of any individual taking part. Achieving such guarantees generally requires the injection…

This paper develops a new physical layer framework for secure two-way wireless communication in the presence of a passive eavesdropper, i.e., Eve. Our approach achieves perfect information theoretic secrecy via a novel randomized scheduling…

The rapid integration of Artificial Intelligence (AI) into medical diagnostics has raised pressing concerns about patient privacy, especially when sensitive imaging data must be transferred, stored, or processed. In this paper, we propose a…

The distribution of entangled quantum systems among two or more nodes of a network is a key task at the basis of quantum communication, quantum computation and quantum cryptography. Unfortunately the transmission lines used in this…