相关论文: Privacy Preserving Properties of Vision Classifier…

Federated learning (FL) allows multiple entities to train a shared model collaboratively. Its core, privacy-preserving principle is that participants only exchange model updates, such as gradients, and never their raw, sensitive data. This…

Artificial intelligence (AI) models are increasingly used in the medical domain. However, as medical data is highly sensitive, special precautions to ensure its protection are required. The gold standard for privacy preservation is the…

Many data mining tasks rely on graphs to model relational structures among individuals (nodes). Since relational data are often sensitive, there is an urgent need to evaluate the privacy risks in graph data. One famous privacy attack…

This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data…

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from…

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…

As a solution concept in cooperative game theory, Shapley value is highly recognized in model interpretability studies and widely adopted by the leading Machine Learning as a Service (MLaaS) providers, such as Google, Microsoft, and IBM.…

Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the…

The expanding usage of complex machine learning methods like deep learning has led to an explosion in human activity recognition, particularly applied to health. In particular, as part of a larger body sensor network system, face and…

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing…

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…

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated…

"Overlearning" means that a model trained for a seemingly simple objective implicitly learns to recognize attributes and concepts that are (1) not part of the learning objective, and (2) sensitive from a privacy or bias perspective. For…

As the privacy risks posed by camera surveillance and facial recognition have grown, so has the research into privacy preservation algorithms. Among these, visual privacy preservation algorithms attempt to impart bodily privacy to subjects…

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

As machine learning (ML) technologies become more prevalent in privacy-sensitive areas like healthcare and finance, eventually incorporating sensitive information in building data-driven algorithms, it is vital to scrutinize whether these…

The massive upsurge in computational and storage has driven the local data and machine learning applications to the cloud environment. The owners may not fully trust the cloud environment as it is managed by third parties. However,…

Gradient inversion attacks are an ubiquitous threat in federated learning as they exploit gradient leakage to reconstruct supposedly private training data. Recent work has proposed to prevent gradient leakage without loss of model utility…

With the extensive applications of machine learning, the issue of private or sensitive data in the training examples becomes more and more serious: during the training process, personal information or habits may be disclosed to unexpected…