Related papers: Taipan: A Query-free Transfer-based Multiple Sensi…
This paper addresses the Multi-Robot Active Information Acquisition (AIA) problem, where a team of mobile robots, communicating through an underlying graph, estimates a hidden state expressing a phenomenon of interest. Applications like…
Graph neural networks (GNNs) excel on homophilic graphs where connected nodes share labels, but struggle with heterophilic graphs where edges do not imply similarity. Moreover, iterative message passing limits scalability due to…
While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract…
Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…
It has been demonstrated that adversarial graphs, i.e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks. In this paper, we extend adversarial graphs to the problem of…
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs beforehand in security-sensitive applications. To efficiently…
Generative Adversarial Networks (GANs) have been widely used for generating synthetic data for cases where there is a limited size real-world dataset or when data holders are unwilling to share their data samples. Recent works showed that…
Studies show that Deep Neural Network (DNN)-based image classification models are vulnerable to maliciously constructed adversarial examples. However, little effort has been made to investigate how DNN-based image retrieval models are…
With the rapid growth of interconnected devices, accurately detecting malicious activities in network traffic has become increasingly challenging. Most existing deep learning-based intrusion detection systems treat network flows as…
Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph…
To mitigate the effects of undesired biases in models, several approaches propose to pre-process the input dataset to reduce the risks of discrimination by preventing the inference of sensitive attributes. Unfortunately, most of these…
Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is…
As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…
Probabilistic Graphical Bayesian models of causation have continued to impact on strategic analyses designed to help evaluate the efficacy of different interventions on systems. However, the standard causal algebras upon which these…
Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles with, enabling multi-hop reasoning. Yet most existing graph-based methods…
Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…
Privacy concerns have become increasingly critical in modern AI and data science applications, where sensitive information is collected, analyzed, and shared across diverse domains such as healthcare, finance, and mobility. While prior…
Certain methods of analysis require the knowledge of the spatial distances between entities whose data are stored in a microdata table. For instance, such knowledge is necessary and sufficient to perform data mining tasks such as nearest…
Membership Inference attacks (MIAs) aim to predict whether a data sample was present in the training data of a machine learning model or not, and are widely used for assessing the privacy risks of language models. Most existing attacks rely…
Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…