Related papers: Private Graph Extraction via Feature Explanations

We study how to communicate findings of Bayesian inference to third parties, while preserving the strong guarantee of differential privacy. Our main contributions are four different algorithms for private Bayesian inference on…

Graph neural networks (GNNs) have achieved tremendous success in the task of graph classification and its diverse downstream real-world applications. Despite the huge success in learning graph representations, current GNN models have…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

The advance of explainable artificial intelligence, which provides reasons for its predictions, is expected to accelerate the use of deep neural networks in the real world like Machine Learning as a Service (MLaaS) that returns predictions…

Federated learning involves a central processor that works with multiple agents to find a global model. The process consists of repeatedly exchanging estimates, which results in the diffusion of information pertaining to the local private…

Reinforcement learning (RL), in conjunction with attack graphs and cyber terrain, are used to develop reward and state associated with determination of optimal paths for exfiltration of data in enterprise networks. This work builds on…

Graph Neural Networks (GNNs) have shown remarkable performance in various applications. Recently, graph prompt learning has emerged as a powerful GNN training paradigm, inspired by advances in language and vision foundation models. Here, a…

Graph neural networks (GNNs) offer promising learning methods for graph-related tasks. However, GNNs are at risk of adversarial attacks. Two primary limitations of the current evasion attack methods are highlighted: (1) The current…

Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…

We propose reconstruction advantage measures to audit label privatization mechanisms. A reconstruction advantage measure quantifies the increase in an attacker's ability to infer the true label of an unlabeled example when provided with a…

Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing their ability to generate structured outputs such as…

Graph neural networks(GNNs) have a wide range of applications in multimedia.Recent studies have shown that Graph neural networks(GNNs) are vulnerable to link stealing attacks,which infers the existence of edges in the target GNN's training…

Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy…

Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other threats like reconstruction attacks attempting to extract…

A growing body of research leverages social network based trust relationships to improve the functionality of the system. However, these systems expose users' trust relationships, which is considered sensitive information in today's…

Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…

Paths in a given network are a generalised form of time-serial chains in many real-world applications, such as trajectories and Internet flows. Differentially private trajectory publishing concerns publishing path information that is usable…

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data reconstruction attacks.…

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving…

Digital presence in the world of online social media entails significant privacy risks. In this work we consider a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such…