Knowledge catalogue
arXiv:2609.16232v1 Announce Type: new Abstract: Geospatial artificial intelligence (GeoAI) powered by large language models (LLMs) is expanding the capacity to query, generate, and interpret spatial i
arXiv:2609.16095v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for improving the quality of generated contents of Large Language Models (LLMs
arXiv:2609.12067v1 Announce Type: new Abstract: Channel simulation has recently emerged as a useful component in machine learning systems where samples from a prescribed probability distribution are t
arXiv:2609.08476v1 Announce Type: cross Abstract: Secure Aggregation (SA) is widely regarded as a strong defense against model-update leakage in Federated Learning (FL), as it reveals only aggregate r
arXiv:2609.05676v1 Announce Type: new Abstract: Language models adapted on private text are often served through APIs, so privacy leakage occurs through generated outputs rather than exposed weights.
arXiv:2608.27954v1 Announce Type: cross Abstract: Post-deployment changes to large language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI gover
arXiv:2608.18610v1 Announce Type: cross Abstract: Dense text embeddings are widely used in data mining, retrieval, and downstream machine learning systems due to their compact and semantically rich re
arXiv:2608.07378v1 Announce Type: cross Abstract: Early diagnosis of Alzheimer's disease (AD) is critical for enabling timely interventions that may slow disease progression and improve patient outcom
arXiv:2608.03130v1 Announce Type: cross Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attribu
arXiv:2608.02774v1 Announce Type: cross Abstract: AI verification crosses a trust boundary: a verifier must learn enough to establish an authorized claim, yet the same evidence can reveal sensitive de
arXiv:2512.12840v2 Announce Type: replace-cross Abstract: Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint f
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 u
arXiv:2510.12780v3 Announce Type: replace-cross Abstract: Voice anonymization techniques have been found to successfully obscure a speaker's acoustic identity in short, isolated utterances in benchmar
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 Li
This paper was accepted at the AI4TCI (Workshop on AI for Secure and Trustworthy Critical Infrastructure Systems) Workshop at the International Conference on Availability, Reliability and Security (AR
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 sign
arXiv:2606.26373v1 Announce Type: cross Abstract: Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector:
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 evalu
arXiv:2606.24941v1 Announce Type: cross Abstract: Reviewing recorded interviews for affective cues such as composure, hesitation and agitation is slow and subjective, and cloud services that could aut
arXiv:2606.25216v1 Announce Type: cross Abstract: Legal requirements might prevent organizations from sharing sensitive data like medical or financial details of consumers which prevents them from lev
arXiv:2606.24938v1 Announce Type: cross Abstract: Tensor decomposition of donor imes cell-type imes gene single-cell data recovers multicellular programs: coordinated axes of inter-individual transcri
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
arXiv:2606.20344v2 Announce Type: replace-cross Abstract: Machine learning models have scaled to unprecedented sizes, making training across distributed devices the de facto standard in the field. In
As expected, yesterday's WWDC keynote was mostly about AI. And also as expected, Apple tried to turn its late arrival into its sales pitch: It didn't rush into AI because it was taking its time to do
arXiv:2606.02483v1 Announce Type: cross Abstract: Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external ser
arXiv:2606.00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire mor
Vultr's data residency solution enables organizations to store and process data within specific geographic regions to meet regulatory compliance requirements such as GDPR, HIPAA, and local data protec
arXiv:2605.28211v1 Announce Type: new Abstract: SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sens
arXiv:2605.24249v1 Announce Type: new Abstract: The growing availability of clinical data has increased the use of machine learning, yet centralized data aggregation is often infeasible for sensitive
arXiv:2605.22924v1 Announce Type: new Abstract: Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at
arXiv:2605.23879v1 Announce Type: cross Abstract: Gradient-flow sampling interprets a Gibbs distribution as the minimizer of an energy functional over probability measures and generates dynamics conve
arXiv:2605.22898v1 Announce Type: new Abstract: Federated learning protocols face a structural trilemma: canonical server-based aggregation~ite{mcmahan2017} creates a single point of failure and gradi
arXiv:2605.17034v1 Announce Type: cross Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individual
arXiv:2605.14123v1 Announce Type: cross Abstract: Feature sharing via split inference offers a lightweight alternative to federated learning for resource-constrained hospitals, but transmitted feature
arXiv:2605.14113v1 Announce Type: cross Abstract: While interpretable prototype networks offer compelling case-based reasoning for clinical diagnostics, their raw continuous outputs lack the semantic
arXiv:2605.13265v1 Announce Type: new Abstract: Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface int
arXiv:2605.08152v1 Announce Type: cross Abstract: The intersection of Artificial Intelligence (AI) and distributed systems has given rise to Federated Learning (FL), a paradigm that enables decentrali
arXiv:2605.04108v1 Announce Type: new Abstract: Federated Learning enables decentralized training by aggregating model updates across clients without sharing raw data, while Split Federated Learning f
arXiv:2605.04221v1 Announce Type: new Abstract: Clinical named entity recognition from dental progress notes is challenging because documentation is highly unstructured, domain-specific, and often pri
arXiv:2604.23688v1 Announce Type: new Abstract: Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective pertu
arXiv:2603.04881v2 Announce Type: replace Abstract: Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade perf
arXiv:2604.12258v1 Announce Type: cross Abstract: Clinical research involves labor-intensive processes such as study design, cohort construction, model development, and documentation, requiring domain
arXiv:2508.19458v2 Announce Type: replace Abstract: A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a
arXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester
arXiv:2610.00822v1 Announce Type: new Abstract: Share the light, not the map. We study next-best-view selection for a team of robots, each of which builds its own 3D Gaussian Splatting map and keeps i
arXiv:2609.26508v1 Announce Type: new Abstract: Streaming principal component analysis (PCA) seeks to recover a leading spectral subspace in a single pass over a data stream. We give a new analysis of
arXiv:2609.19337v1 Announce Type: new Abstract: We present Personalized Federated Hierarchical Gaussian Processes (pFedHGP) for probabilistic regression and classification when data are distributed ac
arXiv:2609.03615v1 Announce Type: new Abstract: While deep generative models offer new opportunities for medical image synthesis and data sharing, their ability to memorize and reproduce training samp
arXiv:2609.03851v1 Announce Type: new Abstract: Federated Learning (FL) with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning. However
arXiv:2608.09328v1 Announce Type: new Abstract: Model learning by an eavesdropper is treated as an estimation problem in a federated environment. The Fisher Information Matrix for the eavesdropper's e
arXiv:2608.05163v1 Announce Type: new Abstract: A common assumption holds that switching to a non-English language makes a multilingual RAG system easier to attack for personal information. We test th
At Bitwize, we've been building Logue, a native macOS app for AI meeting notes and writing, and we just open-sourced it (MIT). We're sharing it here because the whole point is that it runs 100% on-dev
arXiv:2607.06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic
arXiv:2607.05996v1 Announce Type: new Abstract: Unlearnable examples keep publicly shared photos from being learned by unauthorized face-recognition models. An imperceptible perturbation, added before
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 cont
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 t
arXiv:2606.22699v1 Announce Type: new Abstract: Frontier multimodal models can guess whether a person is lying from a testimony video. To do so, they stream that raw face and voice to a third-party mo
arXiv:2605.31167v1 Announce Type: new Abstract: Assessing whether Large Language Models outputs are factually grounded, epistemically calibrated, and methodologically reproducible is a prerequisite fo
arXiv:2506.09521v2 Announce Type: replace-cross Abstract: Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To eva
arXiv:2607.23649v1 Announce Type: new Abstract: Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled