Search: “privacy”

arXiv:2609.10935v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model, a privacy risk that matters in natural langu

arXiv:2609.07063v1 Announce Type: new Abstract: Built upon local differential privacy (LDP), locally private graph learning protocols have emerged as an important paradigm for decentralized graph lear

arXiv:2609.01667v1 Announce Type: cross Abstract: Artificial Intelligence has shown to help improve agricultural practices, yet adoption remains limited: 69% of U.S. farmers have privacy concerns with

arXiv:2608.30951v1 Announce Type: new Abstract: The rapid development of generative portrait models has raised growing concerns about privacy leakage and identity misuse. In particular, audio-driven 3

arXiv:2608.28909v1 Announce Type: new Abstract: Large-scale, publicly available datasets have driven advances in deep learning, but privacy and legal restrictions often limit data sharing in medical i

arXiv:2608.29624v1 Announce Type: new Abstract: Natural Language Processing methods have enabled novel solutions and advances in the field of privacy, particularly in the sub-domain of text-to-text pr

arXiv:2608.26081v1 Announce Type: cross Abstract: Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social

arXiv:2607.29675v1 Announce Type: cross Abstract: Density modes provide a localized and interpretable summary of multimodal distributions, but their estimation under rigorous differential privacy cons

arXiv:2607.27764v1 Announce Type: new Abstract: Publishing private face recognition~(FR) training datasets is privacy-sensitive because faces expose identity information. Private FR training dataset p

arXiv:2508.10017v2 Announce Type: replace-cross Abstract: Federated Learning (FL) presents a groundbreaking approach for collaborative health research, allowing model training on decentralized data wh

arXiv:2510.05416v3 Announce Type: replace Abstract: Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks.

arXiv:2607.13045v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a key paradigm for privacy-preserving collaborative model training across distributed and heterogeneous data so

arXiv:2602.06838v3 Announce Type: replace Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments,

arXiv:2512.23816v2 Announce Type: replace-cross Abstract: In this paper, we study the private and robust alignment of language models from a theoretical perspective by establishing upper bounds on the

arXiv:2603.13293v2 Announce Type: replace Abstract: Accurate cardiovascular risk prediction is crucial for preventive healthcare; however, the development of robust Artificial Intelligence (AI) models

arXiv:2601.09166v3 Announce Type: replace Abstract: Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for pri

arXiv:2606.21107v1 Announce Type: new Abstract: Differential privacy (DP) has become the gold standard for ensuring the privacy protection of machine learning and statistical algorithms in recent deca

arXiv:2508.05212v2 Announce Type: replace-cross Abstract: With the development of big data and machine learning, privacy concerns have become increasingly critical, especially when handling heterogene

arXiv:2506.01396v2 Announce Type: replace Abstract: Differential privacy (DP) has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often ha

arXiv:2511.14019v3 Announce Type: replace Abstract: Robust and privacy-preserving indoor scene understanding remains a fundamental open problem. While optical sensors such as RGB and LiDAR offer high

arXiv:2409.01062v4 Announce Type: replace-cross Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models. While exi

arXiv:2605.30848v1 Announce Type: cross Abstract: Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-ident

arXiv:2603.07551v2 Announce Type: replace-cross Abstract: Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS

arXiv:2410.19371v3 Announce Type: replace-cross Abstract: Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in

arXiv:2602.15919v2 Announce Type: replace-cross Abstract: Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted appro

arXiv:2601.04275v2 Announce Type: replace-cross Abstract: Machine unlearning aims to selectively remove the influence of specific training samples to satisfy privacy regulations such as the GDPR's 'Ri

arXiv:2605.24879v1 Announce Type: new Abstract: Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for f

arXiv:2605.18850v1 Announce Type: cross Abstract: We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to efficiently acc

arXiv:2510.06719v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application i

arXiv:2602.07126v2 Announce Type: replace Abstract: Synthetic tabular data has gained attention for enabling privacy-preserving data sharing. While substantial progress has been made in single-table s

arXiv:2605.01492v1 Announce Type: cross Abstract: We study high-dimensional LASSO under differential privacy via objective perturbation with heterogeneous covariate scales. In practical scenarios, cov

arXiv:2604.23904v1 Announce Type: cross Abstract: Synthetic data offers a promising tool for privacy-preserving data release, augmentation, and simulation, but its use in causal inference requires pre

arXiv:2602.12708v2 Announce Type: replace Abstract: Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance a

arXiv:2604.18716v1 Announce Type: cross Abstract: Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine c

arXiv:2512.09953v2 Announce Type: replace-cross Abstract: Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety require

arXiv:2512.06713v3 Announce Type: replace-cross Abstract: Current LLM-based frameworks for text anonymization usually rely on remote API services from powerful LLMs, which creates an inherent privacy

arXiv:2601.12104v2 Announce Type: replace-cross Abstract: Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Mem

arXiv:2512.01708v2 Announce Type: replace-cross Abstract: Learning the structure of a Bayesian network from decentralized data poses two major challenges: (i) ensuring rigorous privacy guarantees for

arXiv:2511.09829v3 Announce Type: replace Abstract: Adversarial patches have emerged as a popular privacy-preserving approach for resisting AI-driven surveillance systems. However, their conspicuous a

arXiv:2604.06492v1 Announce Type: new Abstract: We study stochastic convex optimization (SCO) with heavy-tailed gradients under pure epsilon-differential privacy (DP). Instead of assuming a bound on t

arXiv:2604.07321v1 Announce Type: cross Abstract: Propositional Linear Temporal Logic (LTL) is a popular formalism for specifying desirable requirements and security and privacy policies for software,

arXiv:2506.10946v3 Announce Type: replace Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing

arXiv:2602.13619v2 Announce Type: replace-cross Abstract: We study parametric change-point detection under local differential privacy, focusing on the offline localization of a single change point in

arXiv:2610.12885v1 Announce Type: new Abstract: Federated Direct Preference Optimization (FedDPO) enables privacy-preserving alignment of language models across distributed agents without centralizing

arXiv:2610.06854v1 Announce Type: cross Abstract: Synthetic data generation is critical for privacy compliance, machine learning augmentation, and software testing. While single-table evaluation is we

arXiv:2508.10020v2 Announce Type: replace-cross Abstract: Enhancing LLM reasoning in federated settings is nontrivial due to stringent computational, communication, and privacy constraints, especially