paper-with-me

홈 › Papers

Helen: Maliciously Secure Coopetitive Learning for Linear Models

2019-07-16 · Wenting Zheng, Raluca Ada Popa, Joseph E. Gonzalez, Ion Stoica

Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). However, they often cannot share their plaintext datasets due to privacy concerns and/or business competition. In this paper, we design and build Helen, a system that allows multiple parties to train a linear model without revealing their data, a setting we call coopetitive learning. Compared to prior secure training systems, Helen protects against a much stronger adversary who is malicious and can compromise m-1 out of m parties. Our evaluation shows that Helen can achieve up to five orders of magnitude of performance improvement when compared to training using an existing state-of-the-art secure multi-party computation framework.

📄 PDF Abstract BibTeX arXiv:1907.07212

Code (0)

등록된 구현이 없습니다.

Tasks

Fraud Detection

Similar Papers 제목 키워드 기반

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

2024-12-15 · Zhendong Mi, Renming Zheng, Haowen Zhong, Yue Sun 외

Recent advances in agentic LLMs have demonstrated great capabilities in Verilog code generation. However, existing approaches either use LLM-assisted single-agent prompting or cooperation-only multi-agent learning, which…

Code GenerationPrompt Learning

FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning

2020-04-05 · Sameer Wagh, Shruti Tople, Fabrice Benhamouda, Eyal Kushilevitz 외

We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high ca…

Deep Learning

A Fast, Performant, Secure Distributed Training Framework For Large Language Model

2024-01-18 · Wei Huang, Yinggui Wang, Anda Cheng, Aihui Zhou 외

The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the server or client side has become an urgen…

Language ModelingLanguage ModellingLarge Language Model

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization

2024-11-16 · Huaqin Zhao, Jiaxi Li, Yi Pan, Shizhe Liang 외

Fine-tuning large language models (LLMs) poses significant memory challenges, as the back-propagation process demands extensive resources, especially with growing model sizes. Recent work, MeZO, addresses this issue usin…

parameter-efficient fine-tuning

From Competition to Coopetition: Coopetitive Training-Free Image Editing Based on Text Guidance

2026-04-17 · Jinhao Shen, Haoqian Du, Xulu Zhang, Xiao-Yong Wei 외 arxiv

Text-guided image editing, a pivotal task in modern multimedia content creation, has seen remarkable progress with training-free methods that eliminate the need for additional optimization. Despite recent progress, exist…

Image Editing