46 articles mentioning privacy-filter
arXiv:2609.03420v1 Announce Type: cross Abstract: Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deployment in operational environments must simultaneously satisfy three competing requirements: formal di
arXiv:2609.02947v1 Announce Type: cross Abstract: Significant challenges remain in AI-driven educational systems in balancing privacy preservation with accurate cognitive diagnosis. To overcome this, we propose a federated inference framework in which several commercial LLM APIs collaborate without
arXiv:2609.02967v1 Announce Type: cross Abstract: Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and intervene on the topology---but they assume one operator can pool all labeled traces. Across organiza
arXiv:2510.20721v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health records
arXiv:2601.19956v2 Announce Type: replace-cross Abstract: As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges: the model is expected to distinguish between users to manage information flow appropriately. Wi
arXiv:2609.02971v1 Announce Type: cross Abstract: As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and infrastructure to train shared models without exposing raw sensor data. Yet the updates clients transmi
The family-focused AI assistant wants access to the details of your everyday life, but says it won’t use that data to train AI models or share it with others.
arXiv:2609.02055v1 Announce Type: cross Abstract: Privacy policies may contain internal contradictions in which commitments are undermined by practices documented elsewhere in the same policy. We operationalize this phenomenon, privacy washing, through a four-stage pipeline: statement extraction, co
arXiv:2609.01273v1 Announce Type: new Abstract: Synthetic data has become a common component of machine learning research. While widely adopted, its use in privacy-sensitive contexts has quietly shifted from a claim of residual inference risk under stated assumptions to an appearance-based property
arXiv:2608.28198v2 Announce Type: replace-cross Abstract: Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve trust and thus participation, improving utility in the long term. However, this claim has not been formalized so far. In parallel, performativ
arXiv:2609.00390v1 Announce Type: cross Abstract: Wearable EEG systems may expose sensitive information beyond their intended health function, creating substantial risks to neuroprivacy. In this work, we show that commonly used EEG features can reveal participant identity and demographic attributes
arXiv:2609.00492v1 Announce Type: new Abstract: Both privacy and factual accuracy are paramount in high-stakes domains like healthcare. Concerningly, we uncover and investigate a privacy-hallucination tradeoff in differentially private (DP) language models. First, we empirically show that models pre
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 evidence is internally inconsistent. Such a scenario exists in real-world healthcare settings, with
arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence privacy-relevant memorization. We examine whether adding synthetic privacy-preference pairs to Direct Pre
arXiv:2608.20118v1 Announce Type: cross Abstract: The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as leukaemia and viral infections. CellCnn, a convolutional neural network (CNN) designed for this task,
arXiv:2606.09590v4 Announce Type: replace Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under realistic threat models. We introduce a clinically grounded framewo
arXiv:2509.10882v2 Announce Type: replace Abstract: In high-stakes domains such as healthcare, privacy concerns severely limit the use of real-world training data. Differentially private (DP) synthetic data offers a promising alternative with formal privacy guarantees, but achieving strong utility r
arXiv:2608.29674v1 Announce Type: new Abstract: Sharing tabular data in high-stakes domains is constrained by privacy regulations. Synthetic data offer a promising alternative, but deep generative models are costly to train and difficult to audit, while LLM-based methods often serialize records as t
arXiv:2605.30123v3 Announce Type: replace-cross Abstract: Homomorphic encryption (HE) enables privacy-preserving aggregation in federated learning (FL) by allowing the server to operate on encrypted data without decryption. Existing HE-over-the-air (OTA) methods mainly rely on single-key HE schemes
arXiv:2608.29111v1 Announce Type: cross Abstract: Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private data. Yet powerful LLMs typically cannot be deployed on the resource-constrained devices where privat
arXiv:2608.27954v2 Announce Type: replace-cross Abstract: Post-deployment changes to large language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI governance when model weights are proprietary. We present a privacy-preserving zk-SNARK-based aud
arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In modern private machine learning applications, achieving strong tradeoffs between utility and theoret
arXiv:2606.26403v2 Announce Type: replace 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 responsib
arXiv:2608.27782v1 Announce Type: cross Abstract: Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP constant for the two that car
arXiv:2608.27066v1 Announce Type: cross Abstract: Privacy-Enhancing Technologies (PETs) in computer vision often rely on noise or image perturbations to protect visual data while securely processing it, creating a trade-off between task performance and protection. This trade-off is commonly evaluate
arXiv:2608.27108v1 Announce Type: cross Abstract: Federated Learning (FL) enables privacy-aware distributed training, yet gradient updates remain exploitable: Man-in-the-Middle (MitM) interception exposes updates in transit, while model poisoning corrupts global convergence. We first introduce GASHE
arXiv:2608.26655v1 Announce Type: new Abstract: Model merging promises to construct a single multi-task model from independently fine-tuned task models without accessing the original task data. This makes it attractive when task data cannot be centralized, but released task models may still leak pri
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 hacking, in which the selected response exploits errors in the proxy reward model, and the absence of
arXiv:2608.25727v1 Announce Type: new 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, their vulnerability to p
arXiv:2305.15148v3 Announce Type: replace Abstract: We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy measurements
arXiv:2410.07632v3 Announce Type: replace Abstract: We study what provable privacy attacks can be shown for trained 2-layer ReLU neural networks, focusing on two types of attacks: membership inference and data reconstruction. We prove that theoretical results on the implicit bias of 2-layer neural n
arXiv:2607.29019v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, but existing pipelines typically operate on plaintext data, raising significant privacy concerns. Prior work on privacy-preserving retrieval leve
arXiv:2607.27940v2 Announce Type: replace-cross Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint, demonstrates that a malicious parameter server can corrupt a PEFT adapter into a privacy b
arXiv:2607.29100v1 Announce Type: new Abstract: Differentially private (DP) training of text-conditioned generative models suffers a utility cliff at strong privacy. We revisit this problem through the geometry of rectified flows: along the straight interpolation between noise and data, the Bayes-op
arXiv:2605.05905v2 Announce Type: replace Abstract: Objective perturbation is a standard mechanism in differentially private empirical risk minimization. In particular, Linear Objective Perturbation (LOP) enforces privacy by adding a random linear term, while strong convexity and stability are ensur
arXiv:2607.28191v1 Announce Type: cross Abstract: Federated learning enables multiple institutions to train shared models without exchanging raw clinical EEG data, but it does not fully prevent privacy leakage from individual model updates. This paper presents a privacy-preserving federated learning
arXiv:2508.07044v2 Announce Type: replace-cross Abstract: Modern music retrieval runs on vector embeddings, and once these embeddings are shared for search or matching they can be copied, probed, or used to train generative models. Fully homomorphic encryption can compute on them but is impractical
arXiv:2607.27815v1 Announce Type: cross Abstract: Local differential privacy (LDP) protocols are vulnerable to poisoning attacks. Existing research have proposed efficient defense strategies for single-item users. However, in practice, a user may possess multiple items. The defense against poisoning
arXiv:2601.04641v2 Announce Type: replace-cross Abstract: The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often di
arXiv:2603.17109v2 Announce Type: replace Abstract: Decoding brain activity into natural language is a major challenge in AI with important applications in assistive communication, neurotechnology, and human-computer interaction. Most existing Brain-Computer Interface (BCI) approaches rely on memory
arXiv:2607.24556v1 Announce Type: new Abstract: Split learning enables collaborative model training by partitioning neural networks across clients and servers. However, improper split placement can lead to severe privacy leakage through intermediate representations. In this work, we propose a topolo
arXiv:2607.23236v1 Announce Type: cross Abstract: Federated learning has achieved considerable success for predictive modelling, yet federated descriptive analytics remains largely unexplored. Existing federated pattern mining approaches are predominantly support-based and do not optimise a principl
arXiv:2607.06608v2 Announce Type: replace-cross Abstract: We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to eng
arXiv:2607.23029v1 Announce Type: new Abstract: Federated learning enables collaborative model training across distributed clients without centralising their data, yet privacy remains a persistent concern because the shared model updates can leak information about local datasets. Existing privacy-pr
arXiv:2606.24941v2 Announce Type: replace-cross Abstract: Reviewing recorded interviews for affective cues such as composure and agitation is slow and subjective, and cloud services that could automate the task require sensitive audio to leave the device. EmotionAI is a fully local Computational Int
arXiv:2607.22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment. While this automation provides clear utility, completing these tasks often requires the insertion o