Novel Evasion Attacks Against Adversarial Training Defense for Smart Grid Federated Learning DOI Creative Commons
Atef H. Bondok, Mohamed Mahmoud, Mahmoud M. Badr

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 112953 - 112972

Published: Jan. 1, 2023

In the advanced metering infrastructure (AMI) of smart grid, meters (SMs) are deployed to collect fine-grained electricity consumption data, enabling billing, load monitoring, and efficient energy management. However, some consumers engage in fraudulent behavior by hacking their meters, leading either traditional theft or more sophisticated evasion attacks (EAs). EAs aim illegally reduce bills while deceiving detection mechanisms. The current methods for identifying such raise privacy concerns due need access consumers' detailed data train To address concerns, federated learning (FL) is proposed as a collaborative training approach across multiple consumers. Adversarial (AT) has shown promise countering threats on machine models. This paper, first, investigates susceptibility classifiers trained FL both independent identically distributed (IID) Non-IID data. Then, it effectiveness AT securing global detector against EAs, assuming no misbehavior from participant process. After that, we introduce three novel attacks, namely Distillation , xmlns:xlink="http://www.w3.org/1999/xlink">No-Adversarial-Sample-Training xmlns:xlink="http://www.w3.org/1999/xlink">False-Labeling which can be launched during process make model susceptible at inference time. Finally, extensive experiments conducted validate severity these attacks. Our findings reveal that counter effectively when participants honest, but fails they act maliciously launch our works lays foundation future endeavors exploring additional countermeasures, conjunction with AT, bolster security resilience models adversarial context detection.

Language: Английский

Anomaly Detection of IoT Cyberattacks in Smart Cities Using Federated Learning and Split Learning DOI Creative Commons
Ishaani Priyadarshini

Big Data and Cognitive Computing, Journal Year: 2024, Volume and Issue: 8(3), P. 21 - 21

Published: Feb. 22, 2024

The swift proliferation of the Internet Things (IoT) devices in smart city infrastructures has created an urgent demand for robust cybersecurity measures. These are susceptible to various cyberattacks that can jeopardize security and functionality urban systems. This research presents innovative approach identifying anomalies caused by IoT cities. proposed method harnesses federated split learning addresses dual challenge enhancing network while preserving data privacy. study conducts extensive experiments using authentic datasets from To compare performance classical machine algorithms deep models detecting anomalies, model effectiveness is assessed precision, recall, F-1 score, accuracy, training/deployment time. findings demonstrate have potential balance privacy concerns with competitive performance, providing solutions cyberattacks. contributes ongoing discussion about securing deployments settings. It lays groundwork scalable privacy-conscious strategies. results underscore vital role these techniques fortifying cities promoting development adaptable resilient measures era.

Language: Английский

Citations

12
A Review of Smart Grid Anomaly Detection Approaches Pertaining to Artificial Intelligence DOI Creative Commons
Marcelo Fabian Guato Burgos, Jorge Morato, Paulina Vizcaíno-Imacaña

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(3), P. 1194 - 1194

Published: Jan. 31, 2024

The size of power grids and a complex technological infrastructure with higher levels automation, connectivity, remote access make it necessary to be able detect anomalies various kinds using optimal intelligent methods. This paper is review studies related the detection in smart AI. Digital repositories were explored considering publications between years 2011 2023. Iterative searches carried out consider different approaches, propose experiments, help identify most applied Seven objects study SG identified: attacks on data integrity, unusual measurements consumptions, intrusions, network infrastructure, electrical data, identification cyber-attacks, use devices. issues relating cybersecurity prove widely studied, especially prevent fraud, falsification, uncontrolled changes model. There clear trend towards conformation anomaly frameworks or hybrid solutions. Machine learning, regression, decision trees, deep support vector machines, neural networks are used. Other proposals presented novel forms, such as federated hyperdimensional computing, graph-based More solutions needed that do not depend lot knowledge AI solve problems generating an evolution what could called next-generation grids. At end this document list acronyms terminology.

Language: Английский

Citations

11
SAARC super smart grid: Navigating the future - unleashing the power of an energy-efficient integration of renewable energy resources in the saarc region DOI
Ali Raza, Marriam Liaqat,

Muhammad Adnan

et al.

Computers & Electrical Engineering, Journal Year: 2024, Volume and Issue: 118, P. 109405 - 109405

Published: July 9, 2024

Language: Английский

Citations

10
Enhancing smart grid load forecasting: An attention-based deep learning model integrated with federated learning and XAI for security and interpretability DOI Creative Commons

Md Al Amin Sarker,

Bharanidharan Shanmugam, Sami Azam

et al.

Intelligent Systems with Applications, Journal Year: 2024, Volume and Issue: 23, P. 200422 - 200422

Published: Aug. 4, 2024

Language: Английский

Citations

8
Advancements in training and deployment strategies for AI-based intrusion detection systems in IoT: a systematic literature review DOI Creative Commons
S Kumar Reddy Mallidi, Rajeswara Rao Ramisetty

Discover Internet of Things, Journal Year: 2025, Volume and Issue: 5(1)

Published: Jan. 22, 2025

Language: Английский

Citations

1
A hybrid learning technique for intrusion detection system for smart grid DOI

Najet Hamdi

Sustainable Computing Informatics and Systems, Journal Year: 2025, Volume and Issue: unknown, P. 101102 - 101102

Published: Feb. 1, 2025

Language: Английский

Citations

1
Economic Cost–Benefit Analysis on Smart Grid Implementation in China DOI Open Access

Newell Sarpong Boateng,

Marco Ciro Liscio, Paolo Sospiro

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(7), P. 2946 - 2946

Published: March 26, 2025

The last Five-Year Plans (2016–2025) in China emphasise economic modernisation, focusing on boosting the services sector, urbanisation, and expansion of social safety net. China’s net-zero strategy targets achieving climate neutrality by 2060, necessitating a transition away from coal toward cleaner energy sources, which accounted for 60.6% total consumption 2023, to Variable Renewable Energy Sources (VRES). By 2021, VRES contributed 23.4% power generation. To integrate VRES, Smart Grids are critical, as they autonomously manage production, distribution, consumption. These grids support industrial residential smart devices, electric vehicle charging, battery storage. This paper applies cost–benefit analysis using customised version Electric Power Research Institute US methodology assess Grid investment 2020 2050. results show benefit-to-cost ratio 6.1:1, demonstrating substantial benefits. focus serves valuable case study implementation worldwide, with adaptable use other countries across different scales. findings can assist global decision-makers evaluating advancement technology, policies, potential impact also comparisons players such US.

Language: Английский

Citations

1
Optimizing Intrusion Detection for IoT: A Systematic Review of Machine Learning and Deep Learning Approaches With Feature Selection and Data Balancing DOI Open Access
S Kumar Reddy Mallidi, Rajeswara Rao Ramisetty

Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, Journal Year: 2025, Volume and Issue: 15(2)

Published: March 28, 2025

ABSTRACT As the Internet of Things (IoT) continues expanding its footprint across various sectors, robust security systems to mitigate associated risks are more critical than ever. Intrusion Detection Systems (IDS) fundamental in safeguarding IoT infrastructures against malicious activities. This systematic review aims guide future research by addressing six pivotal questions that underscore development advanced IDS tailored for environments. Specifically, concentrates on applying machine learning (ML) and deep (DL) technologies enhance capabilities. It explores feature selection methodologies aimed at developing lightweight solutions both effective efficient scenarios. Additionally, assesses different datasets balancing techniques, which crucial training models perform accurately reliably. Through a comprehensive analysis existing literature, this highlights significant trends, identifies current gaps, suggests studies optimize frameworks ever‐evolving landscape.

Language: Английский

Citations

1
A Collaborative Software Defined Network-Based Smart Grid Intrusion Detection System DOI Creative Commons
Sotiris Chatzimiltis, Mohammad Shojafar, Mahdi Boloursaz Mashhadi

et al.

IEEE Open Journal of the Communications Society, Journal Year: 2024, Volume and Issue: 5, P. 700 - 711

Published: Jan. 1, 2024

Current technological advancements in Software Defined Networks (SDN) can provide efficient solutions for smart grids (SGs). An SDN-based SG promises to enhance the efficiency, reliability and sustainability of communication network. However, new security breaches be introduced with this adaptation. A layer defence against insider attacks established using machine learning based intrusion detection system (IDS) located on SDN application layer. Conventional centralised practises, violate user data privacy aspect, thus distributed or collaborative approaches adapted so that detected actions taken. This paper proposes a architecture, highlighting existence IDSs We implemented meter (SM) (SM-IDS), by adapting split methodology. Finally, comparison federated neighbourhood area network (NAN) IDS was made. Numerical results showed, five class classification accuracy over 80.3% F1-score 78.9 SM-IDS technique. Also, NAN-IDS exhibit an 81.1% 79.9.

Language: Английский

Citations

8
Distributed intelligence for IoT-based smart cities: a survey DOI
Mohamed Hashem, Aisha Siddiqa, Fadele Ayotunde Alaba

et al.

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(27), P. 16621 - 16656

Published: July 22, 2024

Language: Английский

Citations

7