Related papers: The Influence of Dropout on Membership Inference i…
Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…
Decision trees are interpretable models that are well-suited to non-linear learning problems. Much work has been done on extending decision tree learning algorithms with differential privacy, a system that guarantees the privacy of samples…
Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training…
So far, privacy models follow two paradigms. The first paradigm, termed inferential privacy in this paper, focuses on the risk due to statistical inference of sensitive information about a target record from other records in the database.…
We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…
Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning…
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…
Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language processing tasks. In…
Predictive machine learning models are becoming increasingly deployed in high-stakes contexts involving sensitive personal data; in these contexts, there is a trade-off between model explainability and data privacy. In this work, we push…
Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…
Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…
Membership inference attacks are one of the simplest forms of privacy leakage for machine learning models: given a data point and model, determine whether the point was used to train the model. Existing membership inference attacks exploit…
Artificial intelligence, machine learning, and deep learning as a service have become the status quo for many industries, leading to the widespread deployment of models that handle sensitive data. Well-performing models, the industry seeks,…
Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using…
Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…
Machine learning models in health care are often deployed in settings where it is important to protect patient privacy. In such settings, methods for differentially private (DP) learning provide a general-purpose approach to learn models…
Model-X knockoff framework offers a model-free variable selection method that ensures finite sample false discovery rate (FDR) control. However, the complexity of generating knockoff variables, coupled with the model-free assumption,…
Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…
Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an…
Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from…