Search: “privacy”

arXiv:2606.04660v1 Announce Type: new Abstract: Lifelong digital companions must integrate cross-session cues, continually update their understanding of users, and adapt to shifting privacy boundaries

arXiv:2601.17130v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are widely used for tasks such as node classification and link prediction, but their use in sensitive settings raises c

arXiv:2606.03358v1 Announce Type: new Abstract: Smart meter data can reveal sensitive socio-demographic characteristics of households, raising privacy concerns. While this risk has been demonstrated a

arXiv:2512.16310v3 Announce Type: replace-cross Abstract: LLM-based agents increasingly use multiple external tools to complete complex tasks. We study Tools Orchestration Privacy Risk (TOP-R): an age

arXiv:2601.21959v2 Announce Type: replace-cross Abstract: We develop a near-optimal testing procedure under the framework of Gaussian differential privacy for simple as well as one- and two-sided test

arXiv:2606.00947v1 Announce Type: cross Abstract: Foundation models are increasingly personalized on decentralized private data through federated learning and are now deployed at scale under growing r

arXiv:2605.30808v1 Announce Type: cross Abstract: Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, post-t

arXiv:2605.30873v1 Announce Type: cross Abstract: Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce

arXiv:2603.18382v2 Announce Type: replace Abstract: Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required special

arXiv:2601.05134v2 Announce Type: replace Abstract: Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches propos

arXiv:2602.09499v2 Announce Type: replace Abstract: We study the computational relationship between replicability (Impagliazzo et al. [STOC `22], Ghazi et al. [NeurIPS `21]) and other stability notion

arXiv:2605.30014v1 Announce Type: new Abstract: Urban trajectories play a crucial role in modeling urban dynamics and supporting various smart city applications. However, privacy concerns restrict acc

arXiv:2605.27892v1 Announce Type: new Abstract: Synthetic Electronic Health Record (EHR) generation provides a promising avenue for data augmentation and cross-hospital modeling in privacy-constrained

arXiv:2605.27219v1 Announce Type: new Abstract: Collaborative analysis of decentralized confidential datasets is important, but direct sharing of original datasets is often restricted by privacy and i

arXiv:2605.06505v2 Announce Type: replace-cross Abstract: We introduce PACZero, a family of PAC-private zeroth-order mechanisms for fine-tuning large language models that delivers usable utility at I(

arXiv:2605.24295v1 Announce Type: new Abstract: We propose PACE-GGM, a data-adaptive differentially private method for covariance estimation that concentrates its privacy budget on the most informativ

arXiv:2602.15602v2 Announce Type: replace Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case

arXiv:2605.23887v1 Announce Type: cross Abstract: Temporal knowledge-graph data marketplaces face three coupled failures in static designs: stale hybrid index shortcuts reduce recall as edges evolve,

arXiv:2602.00688v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as training data extraction (TDE) attacks can expose highly

This post appears to express concerns about OpenAI's data privacy practices and potential government data sharing, though the claim lacks specific evidence or context. Gary Marcus, an AI researcher an

arXiv:2605.20341v1 Announce Type: new Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is co

arXiv:2503.02161v3 Announce Type: replace Abstract: Synthetic tabular data are increasingly being used to replace real data, serving as an effective solution that simultaneously protects privacy and a

arXiv:2605.17758v1 Announce Type: new Abstract: Synthetic data is widely used in healthcare to create datasets that are similar to original data but without the privacy concerns. Generating and evalua

arXiv:2506.15588v2 Announce Type: replace Abstract: Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead

arXiv:2605.15763v1 Announce Type: cross Abstract: Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprietary LLMs, raising data privacy concerns. We demonst

arXiv:2511.14715v3 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who

arXiv:2602.22611v2 Announce Type: replace Abstract: In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties o

arXiv:2601.17644v3 Announce Type: replace-cross Abstract: The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA) introduces impor

arXiv:2605.03426v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance, yet strict data-sharing constraints rend

arXiv:2605.01735v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy

arXiv:2603.01444v2 Announce Type: replace Abstract: Synthetic data generation is an important capability for privacy-preserving data sharing, system benchmarking and test data provisioning. For mixed-

arXiv:2604.27804v1 Announce Type: new Abstract: The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and us

arXiv:2601.03266v2 Announce Type: replace Abstract: Large language models (LLMs) have rapidly advanced in clinical decision-making, yet the deployment of proprietary systems is hindered by privacy con

arXiv:2511.20211v2 Announce Type: replace Abstract: Transparency-aware generation requires modeling not only RGB appearance but also alpha-based opacity and cross-layer composition, which are essentia

arXiv:2506.20941v3 Announce Type: replace Abstract: Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, o

arXiv:2604.23635v1 Announce Type: cross Abstract: Domestic voice assistants and smart-home devices are increasingly embedded in everyday routines, yet their ethics are often treated as an afterthought

arXiv:2604.22795v1 Announce Type: cross Abstract: This study presents a multi-agent reinforcement learning (MARL) framework for load-constrained wind farm flow control (WFFC). While wake steering can

arXiv:2604.23437v1 Announce Type: cross Abstract: The global financial ecosystem confronts a critical asymmetry: while fraud syndicates operate as borderless, distributed networks, banking institution

arXiv:2509.25003v2 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of t

arXiv:2510.01857v3 Announce Type: replace Abstract: Current approaches to improving reasoning in large language models (LLMs) primarily rely on either supervised fine-tuning (SFT) over expert traces o

arXiv:2604.19118v1 Announce Type: cross Abstract: Modern distributed systems generate massive volumes of log data that are critical for detecting anomalies and cyber threats. However, in real world se

arXiv:2510.11251v2 Announce Type: replace-cross Abstract: The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and i

arXiv:2604.17870v1 Announce Type: new Abstract: Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve p

arXiv:2604.17581v1 Announce Type: new Abstract: How much data is enough to make a scientific discovery? As biomedical datasets scale to millions of samples and AI models grow in capacity, progress inc

As AI assistants and privacy proxies challenge the capabilities of traditional bot detection, the Web needs new models for accountability. We believe that control should remain with the client, and th

arXiv:2506.02541v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) can recognize individuals in images and disclose sensitive personal information about them, raising criti