Related papers: Can Differentially Private Fine-tuning LLMs Protec…
Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely…
Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…
We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same $(\varepsilon, \delta)$-DP guarantee using…
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…
We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…
The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of…
Local Differential Privacy (LDP) offers strong privacy protection, especially in settings in which the server collecting the data is untrusted. However, designing LDP mechanisms that achieve an optimal trade-off between privacy, utility and…
The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requires to specify a uniform privacy level $\varepsilon$ that…
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more…
With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…
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…
With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with…
In the past decade analysis of big data has proven to be extremely valuable in many contexts. Local Differential Privacy (LDP) is a state-of-the-art approach which allows statistical computations while protecting each individual user's…
Nowadays, the ubiquitous usage of mobile devices and networks have raised concerns about the loss of control over personal data and research advance towards the trade-off between privacy and utility in scenarios that combine exchange…
Differential Privacy (DP) provides a rigorous framework for releasing statistics while protecting individual information present in a dataset. Although substantial progress has been made on differentially private linear regression, existing…
The leakage of data might have been an extreme effect on the personal level if it contains sensitive information. Common prevention methods like encryption-decryption, endpoint protection, intrusion detection system are prone to leakage.…
Privacy risks in differentially private (DP) systems increase significantly when data is correlated, as standard DP metrics often underestimate the resulting privacy leakage, leaving sensitive information vulnerable. Given the ubiquity of…
Local differential privacy (LDP) has emerged as a promising paradigm for privacy-preserving data collection in distributed systems, where users contribute multi-dimensional records with potentially correlated attributes. Recent work has…
Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…
Federated Learning (FL) enables collaborative model training without direct data sharing, yet it remains vulnerable to privacy attacks such as model inversion and membership inference. Existing differential privacy (DP) solutions for FL…