相关论文: Feature Inference Attack on Shapley Values

A variety of recent papers discuss the application of Shapley values, a concept for explaining coalitional games, for feature attribution in machine learning. However, the correct way to connect a machine learning model to a coalitional…

Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns…

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…

With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…

Federated Learning (FL) is widely recognized as a privacy-preserving Machine Learning paradigm due to its model-sharing mechanism that avoids direct data exchange. Nevertheless, model training leaves exploitable traces that can be used to…

In this paper, we initiate the study of local model reconstruction attacks for federated learning, where a honest-but-curious adversary eavesdrops the messages exchanged between a targeted client and the server, and then reconstructs the…

With the adoption of machine learning-based solutions in routine clinical practice, the need for reliable interpretability tools has become pressing. Shapley values provide local explanations. The method gained popularity in recent years.…

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…

Data valuation has become an increasingly significant discipline in data science due to the economic value of data. In the context of machine learning (ML), data valuation methods aim to equitably measure the contribution of each data point…

The proliferation of large models has intensified the need for efficient data valuation methods to quantify the contribution of individual data providers. Traditional approaches, such as game-theory-based Shapley value and…

Originally introduced in cooperative game theory, Shapley values have become a very popular tool to explain machine learning predictions. Based on Shapley's fairness axioms, every input (feature component) gets a credit how it contributes…

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

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…

Explainable AI (XAI) is critical for ensuring transparency, accountability, and trust in machine learning systems as black-box models are increasingly deployed within high-stakes domains. Among XAI methods, Shapley values are widely used…

Feature attributions based on the Shapley value are popular for explaining machine learning models; however, their estimation is complex from both a theoretical and computational standpoint. We disentangle this complexity into two factors:…

Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized. However, recent studies have revealed that the training…

Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures…

Data valuation aims to quantify the usefulness of individual data sources in training machine learning (ML) models, and is a critical aspect of data-centric ML research. However, data valuation faces significant yet frequently overlooked…

Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedicated to bringing the obscurity of DNNs to light, they…

The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing [16] showing that it is the \emph{unique} method…