Research map / Federated learning and privacy / Privacy attacks and secure learning
Privacy Attacks on Schedule-Driven Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the published schedule to infer candidate private weights via inverse scheduling instead of guessing randomly | TWCT schedules · Synthetic schedules matching the motivating example | TPL | Helped |
| Use an informed inverse-scheduling attack rather than an uninformed random-guessing attack | Published schedules · Synthetic TWCT schedules | TPL | Helped |
| Increase the number of candidate guesses in an uninformed attack | Uninformed privacy-loss benchmark · Private feature domains | expected TPL bounds | Hurt |
Closest papers by meaning
- Privacy-and-Utility-Aware Publishing of Schedules (AAAI 2025 · similarity 0.93)
- Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM (NeurIPS 2017 · similarity 0.84)
- The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD (ICLR 2025 · similarity 0.82)
- An Information-Flow Perspective on Algorithmic Fairness (AAAI 2024 · similarity 0.82)
- Distributed Differentially Private Data Analytics via Secure Sketching (ICML 2025 · similarity 0.82)
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · similarity 0.82)
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.