ML Security PapersA Theoretical Analysis of Detecting Large Model-Generated Time Series
Junji Hou , Junzhou Zhao , Shuo Zhang , Pinghui Wang
Published on arXiv
2511.07104
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
UCE consistently outperforms state-of-the-art baselines across 32 datasets for detecting model-generated time series, validated by both theoretical proof and empirical experiments
UCE (Uncertainty Contraction Estimator)
Novel technique introduced
Motivated by the increasing risks of data misuse and fabrication, we investigate the problem of identifying synthetic time series generated by Time-Series Large Models (TSLMs) in this work. While there are extensive researches on detecting model generated text, we find that these existing methods are not applicable to time series data due to the fundamental modality difference, as time series usually have lower information density and smoother probability distributions than text data, which limit the discriminative power of token-based detectors. To address this issue, we examine the subtle distributional differences between real and model-generated time series and propose the contraction hypothesis, which states that model-generated time series, unlike real ones, exhibit progressively decreasing uncertainty under recursive forecasting. We formally prove this hypothesis under theoretical assumptions on model behavior and time series structure. Model-generated time series exhibit progressively concentrated distributions under recursive forecasting, leading to uncertainty contraction. We provide empirical validation of the hypothesis across diverse datasets. Building on this insight, we introduce the Uncertainty Contraction Estimator (UCE), a white-box detector that aggregates uncertainty metrics over successive prefixes to identify TSLM-generated time series. Extensive experiments on 32 datasets show that UCE consistently outperforms state-of-the-art baselines, offering a reliable and generalizable solution for detecting model-generated time series.
Key Contributions
- Introduces the contraction hypothesis: model-generated time series exhibit progressively decreasing uncertainty under recursive forecasting, proven under formal theoretical assumptions
- Proposes UCE (Uncertainty Contraction Estimator), a white-box detector that aggregates uncertainty over successive prefixes to identify TSLM-generated time series
- Demonstrates that text-based AI-content detectors fail for time series due to lower information density and smoother distributions, motivating a modality-specific approach
🛡️ Threat Analysis
Directly addresses AI-generated content detection — identifying synthetic time series produced by Time-Series Large Models. UCE is a novel detection architecture grounded in new theoretical foundations (the contraction hypothesis), not merely an application of existing methods to a new domain. This is output integrity/provenance for a new modality.