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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| subsample m rows of the gradient matrix instead of all M neurons | mHSSP attacks · CIFAR-10 | running time and success rate: m from 10 to 500, B=10 | Improved |
| use all M rows (m=M) instead of subsampling | mHSSP attacks · CIFAR-10 | running time: B=10 | Hurt |
| use multivariate or statistical attack instead of NS attack | mHSSP attacks · CIFAR-10 | running time: m=2B for NS vs m≈B^2 | Improved |
| samples with repeated labels (40 cat images) | mHSSP attacks · CIFAR-10 same-class batch | reconstruction quality: B=40 | No clear effect |
| compare with gradient inversion attacks at large batch sizes | empirical gradient inversion attacks · batch size 128 or 256 | reconstruction effectiveness: B=128, 256 | Hurt |
Closest papers by meaning
- A New Federated Learning Framework Against Gradient Inversion Attacks (AAAI 2025 · similarity 0.90)
- Concealing Sensitive Samples against Gradient Leakage in Federated Learning (AAAI 2024 · similarity 0.89)
- Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective (AAAI 2024 · similarity 0.89)
- SPEAR: Exact Gradient Inversion of Batches in Federated Learning (NeurIPS 2024 · similarity 0.89)
- Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning (CVPR 2025 · similarity 0.88)
- High-Fidelity Gradient Inversion in Distributed Learning (AAAI 2024 · similarity 0.88)
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.
