Knowledge catalogue
arXiv:2606.09125v1 Announce Type: cross Abstract: Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. Howe
arXiv:2606.09582v1 Announce Type: new Abstract: Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide pri
arXiv:2606.07175v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitiv
arXiv:2605.01679v1 Announce Type: cross Abstract: Fall detection is a critical task in healthcare, particularly for elderly people. Timely fall detection and treatment can prevent severe injuries. Sen
arXiv:2602.00417v2 Announce Type: replace-cross Abstract: We present the first algorithms for generalized linear contextual bandits under shuffle differential privacy and joint differential privacy. W
arXiv:2604.24326v1 Announce Type: cross Abstract: The decentralization of modern energy systems is transforming consumers into prosumers who continuously exchange data with aggregators, peers, and mar
arXiv:2604.13474v1 Announce Type: cross Abstract: We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering bot
arXiv:2610.08831v1 Announce Type: cross Abstract: As the use of smart devices continues to increase, their potential to capture sensitive speech content raises growing privacy concerns. It is therefor
arXiv:2610.04600v1 Announce Type: new Abstract: Best arm identification under differential privacy is a pure-exploration problem in which both statistical efficiency and privacy protection must be ach
arXiv:2601.22434v2 Announce Type: replace-cross Abstract: Training generative machine learning models to produce synthetic tabular data has become a popular approach for enhancing privacy in data shar
arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of
arXiv:2609.11780v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are widely used to audit the privacy disclosure risk of machine learning models, however current state-of-the-art at
arXiv:2609.10608v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in generative tasks across various areas, however their training process raises significant privacy
arXiv:2609.10627v1 Announce Type: cross Abstract: Machine learning explanations reveal model behavior beyond predictions, creating attack surfaces for model confidentiality and data privacy. We system
arXiv:2609.03420v1 Announce Type: cross Abstract: Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deploy
arXiv:2608.10891v1 Announce Type: new Abstract: Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time s
arXiv:2601.19618v2 Announce Type: replace Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is t
arXiv:2607.06037v1 Announce Type: cross Abstract: A shared electrocardiogram (ECG) is itself a biometric fingerprint that can re-identify a patient and reveal personal information. Recent ECG anonymiz
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
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 database
arXiv:2603.12598v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have shown remarkable potential across a wide array of vision-language tasks, leading to their adoption in crit
arXiv:2606.02563v1 Announce Type: new Abstract: Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets (arepsilon_i) according to insti
arXiv:2511.16940v3 Announce Type: replace Abstract: Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individua
arXiv:2605.24458v1 Announce Type: cross Abstract: The integration of fairness and privacy in centralized data-driven applications is critical, especially as these systems increasingly influence sector
arXiv:2408.15621v3 Announce Type: replace Abstract: The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients.
arXiv:2605.05017v1 Announce Type: cross Abstract: Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI so
arXiv:2504.10808v3 Announce Type: replace Abstract: Detecting empathy from video interactions has emerging applications, yet raw videos that could be used for training AI models are rarely available d
arXiv:2411.16121v3 Announce Type: replace-cross Abstract: In recent years, the growth of data across various sectors, including healthcare, security, finance, and education, has created significant op
The practice of privacy-led user experience (UX) is a design philosophy that treats transparency around data collection and usage as an integral part of the customer relationship. An undertapped oppor
arXiv:2604.12342v1 Announce Type: cross Abstract: Training models on a carefully chosen portion of data rather than the full dataset is now a standard preprocess for modern ML. From vision coreset sel
arXiv:2601.09152v2 Announce Type: replace Abstract: Prior work on LLM-based privacy focuses on norm judgment over synthetic vignettes, rather than how people think about a specific data practice and f
arXiv:2604.06518v1 Announce Type: cross Abstract: Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and ins
arXiv:2604.08037v1 Announce Type: cross Abstract: Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech
arXiv:2609.38339v1 Announce Type: cross Abstract: Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly trai
arXiv:2609.38289v1 Announce Type: cross Abstract: In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broad
arXiv:2602.01928v3 Announce Type: replace-cross Abstract: Privacy preservation is critical in many high-stakes domains such as medicine and finance, where sensitive data must be analyzed without compr
arXiv:2609.18864v1 Announce Type: cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unaut
arXiv:2608.26324v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward h
arXiv:2608.18274v1 Announce Type: cross Abstract: OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and
arXiv:2608.12911v1 Announce Type: new Abstract: While the privacy risks of multimodal large language models (MLLMs) have drawn significant attention, the unique vulnerabilities of domain-specific MLLM
arXiv:2608.09164v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms.
arXiv:2603.27117v2 Announce Type: replace-cross Abstract: This paper investigates how gender shapes privacy decision-making in youth smart voice assistant (SVA) ecosystems. Using survey data from 469
arXiv:2604.00209v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private
arXiv:2602.17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in k steps chosen randomly and uniformly from a
arXiv:2605.27292v1 Announce Type: new Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bo
arXiv:2605.26243v1 Announce Type: new Abstract: Graph neural networks (GNNs) achieve strong performance on relational data, but real-world graphs are often distributed across organizations that cannot
arXiv:2605.15246v1 Announce Type: new Abstract: Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generati
arXiv:2508.21146v2 Announce Type: replace Abstract: Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely
arXiv:2605.09232v1 Announce Type: cross Abstract: The increasing deployment of Internet-of-Things (IoT) devices has accelerated the use of distributed learning frameworks, where data remains local whi
arXiv:2605.03945v1 Announce Type: new Abstract: Standard differential privacy imposes uniform privacy constraints across all features, overlooking the inherent distinction between sensitive and insens
arXiv:2604.20904v1 Announce Type: cross Abstract: Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI)
arXiv:2604.19653v1 Announce Type: new Abstract: Human mobility data are used in numerous applications, ranging from public health to urban planning. Human mobility is inherently sensitive, as it can c
arXiv:2602.20743v2 Announce Type: replace Abstract: Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation var
arXiv:2604.18352v1 Announce Type: cross Abstract: State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarant
arXiv:2507.15836v2 Announce Type: replace Abstract: In this work we study black-box privacy auditing, where the goal is to lower bound the privacy parameter of a differentially private learning algori
arXiv:2609.23521v1 Announce Type: new Abstract: Residential traffic classification supports service management, but learning across homes must account for heterogeneous traffic and privacy constraints
arXiv:2604.01113v2 Announce Type: replace Abstract: Large language model (LLM) systems are increasingly used to support high-stakes decision-making, but they typically perform worse when the available
arXiv:2608.16905v1 Announce Type: cross Abstract: While the existence of postmortem privacy is increasingly acknowledged (such as the protection of the presence of deceased within digital spaces), far
arXiv:2608.16461v1 Announce Type: cross Abstract: Central Bank Digital Currency (CBDC)-based welfare schemes may be potentially privacy invasive as they process significant volumes of beneficiary pers
arXiv:2606.17035v2 Announce Type: replace Abstract: Prior research suggests that differential privacy (DP) inherently enhances the robustness of federated learning (FL) against backdoor attacks. In th