AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Beyond Gradient Inversion: Hidden Subset Sum Problem-Based Input Reconstruction for Federated Learning

Qiongxiu Li, Lixia Luo, Agnese Gini, Changlong Ji, Zhanhao Hu, Xiao Li, Chengfang Fang, Jie Shi, Xiaolin Hu

TPAMI 2026 · Federated learning and privacy › Privacy attacks and secure learning · approach: Gradient inversion attacks · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
subsample m rows of the gradient matrix instead of all M neuronsmHSSP attacks · CIFAR-10running time and success rate: m from 10 to 500, B=10Improved
use all M rows (m=M) instead of subsamplingmHSSP attacks · CIFAR-10running time: B=10Hurt
use multivariate or statistical attack instead of NS attackmHSSP attacks · CIFAR-10running time: m=2B for NS vs m≈B^2Improved
samples with repeated labels (40 cat images)mHSSP attacks · CIFAR-10 same-class batchreconstruction quality: B=40No clear effect
compare with gradient inversion attacks at large batch sizesempirical gradient inversion attacks · batch size 128 or 256reconstruction effectiveness: B=128, 256Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy