Impact of Data Poisoning Attacks on Feasibility and Optimality of Neural Power System Optimizers
On the map: LLM safety and security → Backdoor and data poisoning attacks
Abstract (arXiv)
The increased integration of clean yet stochastic energy resources and the growing number of extreme weather events are narrowing the decision-making window of power grid operators. This time constraint is fueling a plethora of research on Machine Learning-, or ML-, based optimization proxies. While finding a fast solution is appealing, the inherent vulnerabilities of the learning-based methods are hindering their adoption. One of these vulnerabilities is data poisoning attacks, which adds perturbations to ML training data, leading to incorrect decisions. The impact of poisoning attacks on learning-based power system optimizers have not been thoroughly studied, which creates a critical vulnerability. In this paper, we examine the impact of data poisoning attacks on ML-based optimization proxies that are used to solve the DC Optimal Power Flow problem. Specifically, we compare the resilience of three different methods-a penalty-based method, a post-repair approach, and a direct mapping approach-against the adverse effects of poisoning attacks. We will use the optimality and feasibility of these proxies as performance metrics. The insights of this work will establish a foundation for enhancing the resilience of neural power system optimizers.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 12 of its 21 references that are in the map. First posted on arXiv 9 Feb 2025.
Builds on
12 of 21 references.
Closest ancestors · 1
Same direction, newest first
Other references · 11
- 2013Intriguing properties of neural networkscited by 5,155
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
- 2021DC3: A learning method for optimization with hard constraintscited by 184
- 2020DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problemscited by 47
- 2023End-to-End Feasible Optimization Proxies for Large-Scale Economic Dispatchcited by 35
- 2022Topology-aware Graph Neural Networks for Learning Feasible and Adaptive ac-OPF Solutionscited by 28
- 2022Learning to Solve Optimization Problems with Hard Linear Constraintscited by 23
- 2019Exploiting Vulnerabilities of Load Forecasting Through Adversarial Attackscited by 18
- 2020DeepOPF+: A Deep Neural Network Approach for DC Optimal Power Flow for Ensuring Feasibilitycited by 11
- 2023BrainWash: A Poisoning Attack to Forget in Continual Learningcited by 9
- 2022Teaching Networks to Solve Optimization Problemscited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective
- 2024A Novel Bifurcation Method for Observation Perturbation Attacks on Reinforcement Learning Agents: Load Altering Attacks on a Cyber Physical Power System
- 2024Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
- 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
- 2024Discovery of False Data Injection Schemes on Frequency Controllers with Reinforcement Learning
- 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Survey
- 2024Inverting Gradient Attacks Makes Powerful Data Poisoning
- 2023Optimal Power Flow in Highly Renewable Power System Based on Attention Neural Networks