Related papers: VaultGemma: A Differentially Private Gemma Model

As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges: the model is expected to distinguish between users to manage information flow appropriately.…

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in…

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

The holy grail of LLM personalization is a single LLM for each user, perfectly aligned with that user's preferences. However, maintaining a separate LLM per user is impractical due to constraints on compute, memory, and system complexity.…

Inspired by the design patterns of object-oriented software architecture, we offer an initial set of "privacy patterns". Our intent is to describe the most important ways in which software systems can offer privacy to their stakeholders. We…

Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks. However, these models have hundreds of billions of parameters, are computationally expensive to run, require users to…

This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of…

The number and dynamic nature of web and mobile applications presents significant challenges for assessing their compliance with data protection laws. In this context, symbolic and statistical Natural Language Processing (NLP) techniques…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…

We propose a hybrid model of differential privacy that considers a combination of regular and opt-in users who desire the differential privacy guarantees of the local privacy model and the trusted curator model, respectively. We demonstrate…

Differential privacy has emerged as the main definition for private data analysis and machine learning. The {\em global} model of differential privacy, which assumes that users trust the data collector, provides strong privacy guarantees…

We introduce Xmodel-1.5, a 1-billion-parameter multilingual large language model pretrained on 2 trillion tokens, designed for balanced performance and scalability. Unlike most large models that use the BPE tokenizer, Xmodel-1.5 employs a…

Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…

We propose a novel federated learning paradigm to model data variability among heterogeneous clients in multi-centric studies. Our method is expressed through a hierarchical Bayesian latent variable model, where client-specific parameters…

PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models. We combine the SigLIP-So400m vision encoder that was also used by PaliGemma with the whole range of Gemma 2 models,…

Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about…

The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…

Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant is local differential privacy, where the data holder is the trusted curator. A major barrier, however, towards a wider adoption of…

We develop differentially private hypothesis testing methods for the small sample regime. Given a sample $\cal D$ from a categorical distribution $p$ over some domain $\Sigma$, an explicitly described distribution $q$ over $\Sigma$, some…