Related papers: Model Inversion Attacks: A Survey of Approaches an…
Skip connections are fundamental architecture designs for modern deep neural networks (DNNs) such as CNNs and ViTs. While they help improve model performance significantly, we identify a vulnerability associated with skip connections to…
An over-the-air membership inference attack (MIA) is presented to leak private information from a wireless signal classifier. Machine learning (ML) provides powerful means to classify wireless signals, e.g., for PHY-layer authentication. As…
Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising concerns about their privacy. To investigate this privacy…
We present a comprehensive analysis of privacy attacks and countermeasures in data-driven systems. We systematically categorize attacks targeting three domains: anonymous data (linkage and structural attacks), statistical aggregates…
Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by observing the prediction output of the ML model. While the key…
Graph Neural Networks (GNNs) are widely adopted to analyse non-Euclidean data, such as chemical networks, brain networks, and social networks, modelling complex relationships and interdependency between objects. Recently, Membership…
Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a severe threat to the security and integrity of pay-per-query…
Machine learning (ML) can help fight pandemics like COVID-19 by enabling rapid screening of large volumes of images. To perform data analysis while maintaining patient privacy, we create ML models that satisfy Differential Privacy (DP).…
Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface…
Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users' membership…
Large language models (LLMs) are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information (PII) in a highly structured and explicit format. As a result, privacy risks arise,…
The utilization of personal sensitive data in training face recognition (FR) models poses significant privacy concerns, as adversaries can employ model inversion attacks (MIA) to infer the original training data. Existing defense methods,…
Learned recommender systems may inadvertently leak information about their training data, leading to privacy violations. We investigate privacy threats faced by recommender systems through the lens of membership inference. In such attacks,…
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…
The last decade has seen a rise of Deep Learning with its applications ranging across diverse domains. But usually, the datasets used to drive these systems contain data which is highly confidential and sensitive. Though, Deep Learning…
Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of…
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on…
Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets…
Collaborative inference (CI) improves computational efficiency for edge devices by transmitting intermediate features to cloud models. However, this process inevitably exposes feature representations to model inversion attacks (MIAs),…
Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…