相关论文: Mitigating Privacy Risk in Membership Inference by…

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership…

In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties of IRs can leak training-set membership signals, enabling Membership Inference Attacks (MIAs)…

A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs,…

With the continued advancement and widespread adoption of machine learning (ML) models across various domains, ensuring user privacy and data security has become a paramount concern. In compliance with data privacy regulations, such as…

In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms…

Federated Learning (FL) has been proposed as a privacy-preserving solution for distributed machine learning, particularly in heterogeneous FL settings where clients have varying computational capabilities and thus train models with…

While many solutions for privacy-preserving convex empirical risk minimization (ERM) have been developed, privacy-preserving nonconvex ERM remains a challenge. We study nonconvex ERM, which takes the form of minimizing a finite-sum of…

Convex optimization finds many real-life applications, where--optimized on real data--optimization results may expose private data attributes (e.g., individual health records, commercial information), thus leading to privacy breaches. To…

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…

Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model…

An over-the-air membership inference attack (MIA) is presented to leak private information from a wireless signal classifier. Machine learning (ML) provides powerful means to classify wireless signals, e.g., for PHY-layer authentication. As…

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m…

Membership inference attacks (MIAs), which determine whether a specific data point was included in the training set of a target model, have posed severe threats in federated learning (FL). Unfortunately, existing MIA defenses, typically…

Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…

Introducing noise in the training of machine learning systems is a powerful way to protect individual privacy via differential privacy guarantees, but comes at a cost to utility. This work looks at whether the inherent randomness of…

To preserve the data privacy, the federated learning (FL) paradigm emerges in which clients only expose model gradients rather than original data for conducting model training. To enhance the protection of model gradients in FL,…

What is the information leakage of an iterative randomized learning algorithm about its training data, when the internal state of the algorithm is \emph{private}? How much is the contribution of each specific training epoch to the…

Convex programming with linear constraints plays an important role in the operation of a number of everyday systems. However, absent any additional protections, revealing or acting on the solutions to such problems may reveal information…

Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and…