Spatio-temporal data-driven detection of false data injection attacks in power distribution systems

Article Engineering, Electrical & Electronic

Coordinated data falsification attack detection in the domain of distributed generation using deep learning

Narayan Bhusal et al.

Summary: This paper proposes a deep learning-based multi-label classification approach to detect coordinated data falsification attacks on distributed generators. The method demonstrates high accuracy across multiple systems.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Authenticating source information of distribution synchrophasors at intra-state locations for cyber-physical resilient power networks

Yi Cui et al.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Detecting False Data Injection Attacks in Smart Grids: A Semi-Supervised Deep Learning Approach

Ying Zhang et al.

Summary: The paper proposes a data-driven learning algorithm for detecting unobservable FDIAs in distribution systems, using autoencoders and a generative adversarial network. By successfully capturing anomalies and only requiring a few labeled data, the method demonstrates high detection accuracy and efficiency in numerical simulations.

IEEE TRANSACTIONS ON SMART GRID (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Generalized attack separation scheme in cyber physical smart grid based on robust interval state estimation

Huaizhi Wang et al.

Summary: This paper introduces a new generalized attack separation scheme in energy internet, which consists of an anomaly detection method and a bad data processor to filter malicious attacks, thereby enhancing the security and stability of smart grids. The proposed scheme shows strong robustness, high stability, and promising performance for attack separation, indicating its high potential for practical implementations in deepcyber penetrated smart grids.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Add to Collection

Article Computer Science, Information Systems

Designing Constraint-Based False Data-Injection Attacks Against the Unbalanced Distribution Smart Grids

Nam N. Tran et al.

Summary: The advent of smart grid and the implementation of state estimation in unbalanced residential distribution grid represent the edge computing-based IoT application. An attack design scheme based on a nonlinear physical-constraint model is proposed to generate false data-injection attacks with theoretically stealthy characteristics. The experimental results show a 100% false-positive rate in bad data detection mechanism and severe consequences of the attack, posing a serious challenge for maintaining the integrity of measurement data for operators.

IEEE INTERNET OF THINGS JOURNAL (2021)

Add to Collection

Article Computer Science, Information Systems

Multi Label Deep Learning classification approach for False Data Injection Attacks in Smart Grid

V. Prasanna Srinivasan et al.

Summary: The smart grid's innovation in replacing the traditional power structure with information creativity poses risks of extreme outcomes from malicious information injection. However, most current methods for detecting FDI attacks are limited to linearized DC power system models and fail to address attacks in AC models, highlighting the need for further development in this area.

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS (2021)

Add to Collection

Article Engineering, Electrical & Electronic