相关论文: Perturbing Inputs to Prevent Model Stealing

Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect…

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Machine Learning (ML) has been widely applied to cybersecurity and is considered state-of-the-art for solving many of the open issues in that field. However, it is very difficult to evaluate how good the produced solutions are, since the…

Machine learning models and their applications, such as autonomous driving systems, are becoming increasingly common and are essential components of human daily life. However, due to their sensitivity to perturbed noise, these models are…

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to…

Machine learning models often pose a threat to the privacy of individuals whose data is part of the training set. Several recent attacks have been able to infer sensitive information from trained models, including model inversion or…

The rise of model sharing through frameworks and dedicated hubs makes Machine Learning significantly more accessible. Despite its benefits, loading shared models exposes users to underexplored security risks, while security awareness…

In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus…

Privacy-preserving analytics is designed to protect valuable assets. A common service provision involves the input data from the client and the model on the analyst's side. The importance of the privacy preservation is fuelled by legal…

The impact of voice disorders is becoming more widely acknowledged as a public health issue. Several machine learning-based classifiers with the potential to identify disorders have been used in recent studies to differentiate between…

Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions. While a large literature has studied the case of test-time attacks on…

The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data…

Collecting web data to train deep models has become increasingly common, raising concerns about unauthorized data usage. To mitigate this issue, unlearnable examples introduce imperceptible perturbations into data, preventing models from…

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Adversarial attacks are a type of attack on machine learning models where an attacker deliberately modifies the inputs to cause the model to make incorrect predictions. Adversarial attacks can have serious consequences, particularly in…

Medical multimodal large language models (MLLMs) are becoming an instrumental part of healthcare systems, assisting medical personnel with decision making and results analysis. Models for radiology report generation are able to interpret…

Detection of emerging attacks on network infrastructure is a critical aspect of security management. To meet the growing scale and complexity of modern threats, machine learning (ML) techniques offer valuable tools for automating the…

Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a…

ML models are increasingly deployed in settings with real world interactions such as vehicles, but unfortunately, these models can fail in systematic ways. To prevent errors, ML engineering teams monitor and continuously improve these…

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…