INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression

2026-04-13

AI Summary

This work addresses the challenge of applying adversarial attacks to time series forecasting under stringent real-time and memory constraints. The authors propose a novel online adversarial attack framework tailored for time series regression with bounded buffering, which strategically integrates model confidence and predicted error estimation to identify critical timesteps. Attacks are sparsely deployed only when the model exhibits high confidence yet is expected to incur maximal prediction error. By synergistically combining a real-time selective attack mechanism, online buffer management, and on-the-fly adversarial perturbation generation, the method achieves up to a 2.42-fold increase in prediction error while maintaining an attack frequency below 10%, substantially outperforming existing approaches.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Time-series forecasting aims to predict future values by modeling temporal dependencies in historical observations. It is a critical component of many real-world systems, where accurate forecasts improve operational efficiency and help mitigate uncertainty and risk. More recently, machine learning (ML), and especially deep learning (DL)-based models, have gained widespread adoption for time-series forecasting, but they remain vulnerable to adversarial attacks. However, many state-of-the-art attack methods are not directly applicable in time-series settings, where storing complete historical data or performing attacks at every time step is often impractical. This paper proposes an adversarial attack framework for time-series forecasting under an online bounded-buffer setting, leveraging an informed and selective attack strategy. By selectively targeting time steps where the model exhibits high confidence and the expected prediction error is maximal, our framework produces fewer but substantially more effective attacks. Experiments show that our framework can increase the prediction error up to 2.42x, while performing attacks in fewer than 10% of time steps.

Problem

• adversarial attacks
• time-series forecasting
• online setting
• bounded-buffer
• prediction error

Innovation

• adversarial attack
• time-series forecasting
• selective attack strategy
• online bounded-buffer
• informed attack