paper-with-me

Papers

Props for Machine-Learning Security

2024-10-27 · Ari Juels, Farinaz Koushanfar

We propose protected pipelines or props for short, a new approach for authenticated, privacy-preserving access to deep-web data for machine learning (ML). By permitting secure use of vast sources of deep-web data, props address the systemic bottleneck of limited high-quality training data in ML development. Props also enable privacy-preserving and trustworthy forms of inference, allowing for safe use of sensitive data in ML applications. Props are practically realizable today by leveraging privacy-preserving oracle systems initially developed for blockchain applications.

📄 PDF Abstract BibTeX arXiv:2410.20522

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

PROPS: Probabilistic personalization of black-box sequence models

2019-03-05 · Michael Thomas Wojnowicz, Xuan Zhao

We present PROPS, a lightweight transfer learning mechanism for sequential data. PROPS learns probabilistic perturbations around the predictions of one or more arbitrarily complex, pre-trained black box models (such as r…

ArticlesLanguage ModelingLanguage ModellingTransfer Learning

miniCodeProps: a Minimal Benchmark for Proving Code Properties

2024-06-16 · Evan Lohn, Sean Welleck

AI agents have shown initial promise in automating mathematical theorem proving in proof assistants such as Lean. The same proof assistants can be used to verify the correctness of code by pairing code with specification…

AI AgentAutomated Theorem Proving

PROPS: Progressively Private Self-alignment of Large Language Models

2025-08-09 · Noel Teku, Fengwei Tian, Payel Bhattacharjee, Souradip Chakraborty 외 arxiv

Alignment is a key step in developing Large Language Models (LLMs) using human feedback to ensure adherence to human values and societal norms. Dependence on human feedback raises privacy concerns about how much a labele…

PropSplat: Map-Free RF Field Reconstruction via 3D Gaussian Propagation Splatting

2026-05-08 · William Bjorndahl, Maninder Pal Singh, Farhad Nouri, Joseph Camp arxiv

Building a site-specific propagation model typically requires either ray-tracing over detailed 3D maps or dense measurement campaigns. Both approaches are expensive and often infeasible for rapid deployments where geogra…

ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions

2026-07-06 · Thomas Thebaud, Junhyeok Lee, Laureano Moro-Velazquez, Jesus Villalba Lopez 외 arxiv

Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed spe…

Voice Conversion