47 articles mentioning privacy-filter
arXiv:2607.14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserv
arXiv:2607.14205v1 Announce Type: new Abstract: Federated learning (FL) enables multi-institutional training on clinical text without sharing raw data, but gradient inversion can reconstruct sensitive information from shared model updates. The extent of this leakage for radiology reports, and the ro
arXiv:2607.13093v1 Announce Type: cross Abstract: On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeas
arXiv:2607.13328v1 Announce Type: cross Abstract: Personalized recommendation systems are central to modern e-commerce and retail platforms, but they typically rely on centralized storage of detailed user interaction data, creating significant privacy and regulatory challenges. With increasing requi
arXiv:2607.13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms. While cloud deployments offer scalable compute, concerns over data sovereignty, complia
arXiv:2607.13046v1 Announce Type: new Abstract: We develop a framework for the information discarded by machine learning models whose inputs carry a Lie group action. Given a representation $\pi$ of a Lie group $G$ on a space $V$ and a learned function $f\colon V \to \mathbb{R}$, we define two objec
arXiv:2607.13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-
arXiv:2607.12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks. We show that extensive exposure can persist without rote memorization and is instea
arXiv:2607.10467v2 Announce Type: replace-cross Abstract: Healthcare organizations often cannot freely centralize patient data because medical records are sensitive, regulated, and institutionally controlled. Federated learning offers a practical alternative by allowing hospitals and clinics to trai
arXiv:2607.12246v1 Announce Type: new Abstract: Personalization in two-sided marketplaces relies heavily on user-level features, yet for platforms with infrequent, high-consideration purchases, a large fraction of users lack sufficient history for effective recommendation, spanning both paid and org
arXiv:2606.26373v4 Announce Type: replace-cross Abstract: Semantic search creates an asymmetric disclosure problem: query embeddings may reveal user intent, while returning exact provider vectors distributes reusable representations. We evaluate a deliberately restricted hybrid design. A public corp
arXiv:2606.02563v2 Announce Type: replace Abstract: Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon
arXiv:2607.11600v1 Announce Type: new Abstract: We propose a collaborative meta-learning framework for distributed Bayesian optimization matching centralized performance without raw-data exchange. We show gradient sharing leaks client observations, with leakage worsening as the search converges and
arXiv:2607.10709v1 Announce Type: cross Abstract: Large Language Model (LLM) services introduce a fundamental privacy challenge. Sensitive information may be inferred not only from explicit identifiers, such as names or phone numbers, but also from contextual associations among otherwise innocuous s
arXiv:2604.07486v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We propose
arXiv:2512.03238v2 Announce Type: replace-cross Abstract: High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated data will soon have been used. Additionally, publicly available
arXiv:2405.16361v4 Announce Type: replace Abstract: To protect privacy in regulated domains such as healthcare and finance, model owners may allow only remote API access while keeping both the training data and model parameters private. However, model users performing inference on such remotely host
arXiv:2607.06127v2 Announce Type: replace Abstract: We present LLM4SDM, the first study of open-source smaller language models (OS-sLLMs) for automated assessment of shared decision making (SDM) using the Observer OPTION12 framework. Unlike previous work that relies on large commercial models and th
arXiv:2607.08402v1 Announce Type: cross Abstract: Large-scale and diverse datasets are needed to train AI models to take real-time decisions for autonomous vehicles (AVs), an intelligent transportation system (ITS) application. Pedestrian intention and trajectory prediction are critical models used
arXiv:2607.07775v1 Announce Type: new Abstract: The human body is at the center of a growing family of technologies designed to tightly and persistently couple biological and digital systems. Robotic prostheses are a representative example of this tight coupling. Also referred to as bionic limbs, ro
arXiv:2607.08659v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level different
arXiv:2607.08595v1 Announce Type: new Abstract: Cardiovascular disease risk prediction models often rely on data from a single institution or centrally pooled datasets. Extending these models across institutions could be limited by privacy regulations and constraints on sharing patient-level data. F
arXiv:2607.08282v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have become essential productivity tools, their integration into workflows without adequate safeguards creates significant risks. This paper proposes an open-source, privacy-focused, user-facing firewall designed to
arXiv:2503.07570v3 Announce Type: replace-cross Abstract: Deep learning, when integrated with a large amount of training data, has the potential to outperform machine learning in terms of high accuracy. Recently, privacy-preserving deep learning has drawn significant attention of the research commun
arXiv:2607.02187v1 Announce Type: new Abstract: Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy leakage and malicious manipulation. Existing defenses typically address these threats in isolation and are of
arXiv:2607.01492v1 Announce Type: new Abstract: Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning. We show that this trilemma does not universally extend to generalization error, but inste
arXiv:2601.22710v2 Announce Type: replace-cross Abstract: Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a deploy
arXiv:2601.14660v2 Announce Type: replace-cross Abstract: Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities are enabling transformative applications in domains spanning from personal assistant, financial, and legal domains
Venice AI is already profitable, with annualized run-rate revenues of over $70 million, CEO Erik Voorhees said.
arXiv:2606.31973v1 Announce Type: cross Abstract: Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw data, enabling efficient and robust communication under resource and channel constraints. In this paper
Proton's Lumo 2.0 is dropping this week, giving users a broader variety of capabilities.
arXiv:2507.04771v2 Announce Type: replace-cross Abstract: Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a pr
arXiv:2601.03546v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate decision-making tasks involving personal data sharing, where privacy concerns and prosocial motivations can push choices in opposite directions. Existing evaluations often measure
arXiv:2606.29567v1 Announce Type: cross Abstract: LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control. When those queries contain personally identifiable information (PII), the data persists on remote infrastructure subject to
arXiv:2606.28479v1 Announce Type: cross Abstract: CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD. We present the first empirical study of how DP SGD and H
arXiv:2606.27936v1 Announce Type: cross Abstract: The widespread collection of fine-grained location data by commercial data brokers creates a re-identification risk that is not widely recognised by the public. While prior research has established that mobility traces are highly unique and that indi
arXiv:2606.27558v1 Announce Type: new Abstract: Fairness measurements in the form of disaggregated evaluations often rely on demographic signals that are legally constrained or culturally sensitive. Race and ethnicity signals are among the more difficult signals to curate and use for this task. This
arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks. However, conventional function-calling benchmarks mainly evaluate ta
arXiv:2606.26664v1 Announce Type: cross Abstract: Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic, large-scale financial graphs
arXiv:2606.26123v1 Announce Type: cross Abstract: Ultra-low latency and high throughput are required for Virtual Reality (VR) services in 6G networks, which presents critical challenges for Software-Defined Radio Access Networks (SD-RANs) dynamic resource management. This work propose a mobility-dri
arXiv:2606.26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes
arXiv:2606.26403v1 Announce Type: new Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly,
arXiv:2606.24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts. To address this, we propose a multi-agent framework that sanitizes
arXiv:2606.25533v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for enhancing large language models with external knowledge. By coupling retrieval mechanisms with generative models, RAG systems improve factual grounding and adaptability acros
arXiv:2405.17423v4 Announce Type: replace-cross Abstract: As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive
arXiv:2606.25627v1 Announce Type: new Abstract: Distributed intelligent systems increasingly need to train across data silos without centralizing raw data. Federated learning keeps data local but can suffer under heterogeneous partitions and requires repeated full-model exchange. Split learning redu
arXiv:2606.24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, most existing methods for auditing differential privacy require the insertion of specially crafted canary data during training, making them impractica