相关论文: MER-Inspector: Assessing model extraction risks fr…

Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluation and benchmark of model robustness. However, current…

Neural networks are valuable intellectual property due to the significant computational cost, expert labor, and proprietary data involved in their development. Consequently, protecting their parameters is critical not only for maintaining a…

Federated learning of deep learning models for supervised tasks, e.g. image classification and segmentation, has found many applications: for example in human-in-the-loop tasks such as film post-production where it enables sharing of domain…

In an era of escalating cyber threats, malware poses significant risks to individuals and organizations, potentially leading to data breaches, system failures, and substantial financial losses. This study addresses the urgent need for…

With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine…

Model Merging (MM) has emerged as a promising alternative to multi-task learning, where multiple fine-tuned models are combined, without access to tasks' training data, into a single model that maintains performance across tasks. Recent…

With the wide-spread application of machine learning models, it has become critical to study the potential data leakage of models trained on sensitive data. Recently, various membership inference (MI) attacks are proposed to determine if a…

Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…

Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers. Recent work has shown that attackers can exploit these APIs to extract good approximations of such…

Various studies among side-channel attacks have tried to extract information through leakages from electronic devices to reach the instruction flow of some appliances. However, previous methods highly depend on the resolution of traced…

In the federated learning system, parameter gradients are shared among participants and the central modulator, while the original data never leave their protected source domain. However, the gradient itself might carry enough information…

Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…

Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliability of machine learning (ML) models in safety-critical systems such as automotive…

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction…

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

Web attacks are one of the major and most persistent forms of cyber threats, which bring huge costs and losses to web application-based businesses. Various detection methods, such as signature-based, machine learning-based, and deep…

Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that…

In this work, we introduce PII-Scope, a comprehensive benchmark designed to evaluate state-of-the-art methodologies for PII extraction attacks targeting LLMs across diverse threat settings. Our study provides a deeper understanding of these…

Machine Learning (ML) models are increasingly deployed in the wild to perform a wide range of tasks. In this work, we ask to what extent can an adversary steal functionality of such "victim" models based solely on blackbox interactions:…

Server breaches are an unfortunate reality on today's Internet. In the context of deep neural network (DNN) models, they are particularly harmful, because a leaked model gives an attacker "white-box" access to generate adversarial examples,…