Research map / Time series / Causal and generative time series
Data Poisoning Attacks against Autoregressive Models
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 |
|---|---|---|---|
| optimal quadratic-program attack instead of Greedy/Random | poisoning initial values of linear AR forecaster · 1,000 random AR models (synthetic) | attacker loss F(delta) | Helped |
| Greedy attack instead of Random | AR poisoning baselines · synthetic AR models | attacker loss | Mixed |
| tighten attacker per-step budget beta | Greedy and Random attackers · US natural gas futures | gap to optimal attack | Helped |
Closest papers by meaning
- BackTime: Backdoor Attacks on Multivariate Time Series Forecasting (NeurIPS 2024 · similarity 0.86)
- Distributional Adversarial Attacks and Training in Deep Hedging (NeurIPS 2025 · similarity 0.82)
- Market-GAN: Adding Control to Financial Market Data Generation with Semantic Context (AAAI 2024 · similarity 0.82)
- Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting (AAAI 2025 · similarity 0.81)
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization (NeurIPS 2025 · similarity 0.81)
- Hedging and Approximate Truthfulness in Traditional Forecasting Competitions (AAAI 2025 · similarity 0.81)
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.