47 articles mentioning privacy-filter
arXiv:2610.27470v1 Announce Type: cross Abstract: Federated learning (FL) is a distributed machine learning paradigm that reduces transmission costs, mitigates cross-border data sharing restrictions, and enhances privacy by keeping raw data on local devices. Clients in FL systems train local models
arXiv:2605.13265v2 Announce Type: replace Abstract: Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server. However, the cut-layer interface introduces a key challenge: high-dimensional activations incur substantial communication overh
arXiv:2610.27026v1 Announce Type: cross Abstract: Traffic cameras support useful analysis, but their outputs can reveal private information. Replacing images with text reduces direct visual exposure. It does not place a formal bound on disclosure. The published reinforcement learning and mixture-of-
arXiv:2610.27021v1 Announce Type: cross Abstract: Statistical privacy audits are essential for verifying the theoretical privacy guarantees of differentially private (DP) mechanisms. Auditors typically use Membership Inference Attacks (MIAs) to estimate a lower bound on the true privacy leakage of D
arXiv:2610.22722v2 Announce Type: replace-cross Abstract: Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is difficult when attackers see different messages, know diff
arXiv:2610.27213v1 Announce Type: cross Abstract: Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests with rich, user-specific facts. This paradigm exposes the user profile itself, together with the user's explicit sharing preferences
arXiv:2610.27710v1 Announce Type: new Abstract: Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (DP) training provides formal guarantees, it comes at a cost in sample quality. In
arXiv:2510.23463v5 Announce Type: replace Abstract: Federated Learning (FL) is a distributed learning paradigm that preserves privacy by eliminating the need to exchange raw data during training. In its prototypical edge instantiation with underlying wireless transmissions enabled by analog over-the
arXiv:2610.28315v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy risk if exposed. We ask how consulting memory during dialogue changes what users go on to say, and th
arXiv:2610.27323v1 Announce Type: cross Abstract: Vision-language models (VLMs) can infer sensitive information such as geolocation from subtle visual cues, creating privacy risks when responses disclose more detail than the visual context warrants. We study visual-contextual privacy in geolocation
arXiv:2610.27817v1 Announce Type: new Abstract: Every prompt sent to a hosted language model is readable by whoever runs it. We study whether the prompt can remain on the client while the host receives transformed vectors that stand in for it. A language model converts text to vectors exactly once,
arXiv:2610.23668v1 Announce Type: cross Abstract: Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fields support downstream decisions but may reveal information beyond a recipient's
arXiv:2610.22659v1 Announce Type: cross Abstract: Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a controlled comparison of data-level and training-level interventions for n
arXiv:2610.22800v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers exposes data subjects and organizations to risks from logging
arXiv:2610.23798v1 Announce Type: cross Abstract: R\`enyi differential privacy, based on R\`enyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, R\`enyi divergence can be difficult to compute. In particular, R\`enyi differential privacy guaran
arXiv:2610.22722v1 Announce Type: cross Abstract: Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is difficult when attackers see different messages, know different mo
arXiv:2610.21194v1 Announce Type: cross Abstract: Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve sensitive information and remain vulnerable to reconstruction attacks. Moreover, their generation often incurs considerable client-side computati
arXiv:2605.02255v2 Announce Type: replace-cross Abstract: Large language models (LLMs) face diverse privacy threats, yet existing studies typically evaluate individual attacks in isolation, offering limited guidance on which system factors drive privacy vulnerabilities. This paper presents a unified
arXiv:2610.20796v1 Announce Type: cross Abstract: Health-misinformation analysis presents a dual challenge: misleading claims can affect public well-being, while systems designed to detect them may expose sensitive user-submitted text. This motivates privacy-preserving inference for public-health ap
arXiv:2606.12733v3 Announce Type: replace Abstract: Privacy auditing provides an important safeguard by estimating the actual information leaked by a model, thus ensuring that theoretical privacy guarantees hold in practice. We study empirical privacy auditing for differentially private (DP) machine
arXiv:2610.21547v1 Announce Type: new Abstract: Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a model from scratch. In this report, prepared for the 4th Federated Machine Learning International Summ
arXiv:2610.21033v1 Announce Type: cross Abstract: We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariate distributions that can be approximated by piece-wise polynomials. This gives the first sample-efficient LDP learners for several
arXiv:2610.21799v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted information from large language models, but existing evaluations often measure forgetting only on a designated benchmark distribution. We argue that such behavioral forgetting is an insufficient standard for p
arXiv:2610.21048v1 Announce Type: new Abstract: Extracting insights from textual data while protecting user privacy is increasingly important. Existing methods produce private insights in diverse forms for different analytical purposes, making their utility difficult to assess and compare. In this w
arXiv:2605.27292v3 Announce Type: replace Abstract: Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters. Standard privacy auditing inserts a sensitive samp
arXiv:2610.21333v1 Announce Type: new Abstract: Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individual's private attributes. We call such a jointly revealing set of cues a quasi-evidence group. Existing privacy benchmarks focus on ex
arXiv:2610.21308v1 Announce Type: cross Abstract: Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text rather than as temporal evidence. This representation is poorly matched to personal health systems tha
Today, I’m talking with Benn Jordan, musician, YouTuber, researcher, and investigative journalist. You might know Benn from those first two titles — he’s got a prolific discography of experimental music dating back decades. But in the last couple of years, he’s become a high-profile face in the crea
arXiv:2610.18294v1 Announce Type: cross Abstract: Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training. We ask whether the choice of optimizer affects the ability to recover the training data. Extend
arXiv:2610.08255v1 Announce Type: cross Abstract: Many organizations adapt large pretrained models to their own tasks by fine-tuning on private data. Several of these parties often hold data for the same task and wish to fine-tune a model together without pooling that data. Federated learning (FL) e
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 therefore critical to develop techniques that prevent information leakage while preserving the utility of th
arXiv:2609.21363v2 Announce Type: replace-cross Abstract: Multimodal large reasoning models (MLRMs) have demonstrated remarkable capabilities in complex visual understanding. However, this very power introduces a critical yet underexplored privacy threat: adversaries can exploit MLRMs to precisely i
arXiv:2609.15039v3 Announce Type: replace-cross Abstract: User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a trusted execution environment (TEE). However, this results in slow inference times as current TEEs a
arXiv:2608.25727v2 Announce Type: replace Abstract: Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving rise to LLM-enhanced GNNs that achieve substantial performance gains. However, how such semantic en
arXiv:2610.07399v1 Announce Type: new Abstract: Federated deep clustering seeks to learn clustering-friendly representations from decentralized unlabeled data while preserving client privacy. However, Deep Embedded Clustering (DEC)-style objectives depend on global soft-assignment statistics that re
arXiv:2610.07677v1 Announce Type: new Abstract: In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standard training techniques such as MixUp and Adversarial
arXiv:2609.38630v2 Announce Type: replace Abstract: Privacy redaction must remove personal information while preserving relationships expressed in text. We develop a multilingual named-entity tagger with fine-grained distinctions supporting varied redaction policies and methods for cheaply learning
arXiv:2610.07212v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) trains a language model on problems that may themselves be confidential, and the trained model can reveal which problems it saw. We study RLVR under prompt-level differential privacy: the released w
The AI lab's personal assistant is an operating system from the future designed to compete with Muse, Dots, and Instinct.
arXiv:2610.02716v1 Announce Type: new Abstract: Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer. We study the finite computation obtained by releasing the $N$-th iterate of deterministic gradient descent on $w\mapsto F(w;S)+
arXiv:2607.02814v2 Announce Type: replace-cross Abstract: Personal AI agents are beginning to negotiate for people, from refunds and bills to deposits and sales. A human agent in that position is judged by the duties owed to the principal, not by whether a deal was struck. We introduce SovereignNego
arXiv:2608.18749v3 Announce Type: replace Abstract: Geometric data perturbation enables one-shot representation sharing for privacy-preserving collaborative learning: each participant applies a secret distance-preserving transformation to its private data and uploads the resulting representation to
arXiv:2610.02504v1 Announce Type: new Abstract: Balancing electricity demand and supply is increasingly difficult due to the inherent intermittency of renewable power generation and the stochastic power consumption. Grid operators require fine-grained, decision-relevant insights into household energ
arXiv:2607.06320v3 Announce Type: replace-cross Abstract: We present the dithered Gaussian mechanism, an alternative to the discrete Gaussian mechanism for differential privacy that discretizes the private output rather than the noise distribution itself. By interpreting this discretization as post-
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 sharing. As this typically involves processing sensitive personal information, releasing either the trai
arXiv:2609.38934v1 Announce Type: cross Abstract: Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement carries about the underlying data. We identify this as an evidence gap: a private report may contain pla
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 broader systems that access, infer, and reuse user information across components and over time. While suc