Mind the Intention: Task-Aware Backdoor Attacks for Forecast-Driven Distribution Network Operations

2026-06-19

AI Summary

This work addresses the threat posed by backdoor attacks in distributed energy forecasting to power grid dispatch, where existing methods fail to explicitly model the attacker’s intent and its impact on downstream operational tasks. To bridge this gap, the authors propose GridTroj, a novel framework that, for the first time, couples adversarial intent with grid operation optimization to establish a task-aware backdoor attack paradigm. GridTroj employs a dual-module architecture: an intent planner generates disruptive strategies targeting specific operational objectives, while a backdoor implementer constructs a trigger-to-target association model, integrating a time-series backdoor mechanism with a tailored training strategy. Experiments across three canonical grid optimization tasks demonstrate that GridTroj significantly outperforms existing baselines, achieving stealthy, efficient, and task-oriented targeted attacks.

Abstract

Accurate distributed energy resources (DERs) forecasting is critical for downstream optimal operations. However, such forecast-based operation can be highly vulnerable to cyberattacks. While existing research mainly focuses on adversarial attacks, we pivot to a more controllable and persistent threat: backdoor attacks. In time series forecasting, a backdoored model generates an attacker-specified target pattern whenever a trigger is embedded in historical inputs. This paradigm naturally fits the entire DER forecast-optimization-operation chain. In this paper, we investigate whether and how backdoor attacks can compromise distribution network operations and propose GridTroj, a unified backdoor framework tailored for this scenario. Unlike standard time series backdoor approaches that train a poisoned model to match a predefined target only in terms of forecasting error, GridTroj explicitly incorporates the attacker's intention and optimizes the attack toward operational disruption. Specifically, GridTroj coordinates two key modules. The Intention Planner designs operation-damaging targets and poisoning strategies, while the Backdoor Realizer constructs the corresponding network architecture and training strategy to learn the trigger-target association. Experiments on three downstream optimization tasks demonstrate that GridTroj can effectively compromise grid operations and outperforms existing baselines. Our code is available at https://github.com/YuxuanCEE/GridTroj.

Problem

• backdoor attacks
• distribution network operations
• forecast-driven optimization
• distributed energy resources
• cybersecurity

Innovation

• backdoor attack
• forecast-driven operation
• intention-aware
• distribution network
• GridTroj