{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T07:53:52Z","timestamp":1768204432099,"version":"3.49.0"},"reference-count":20,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>As machine learning models continue to advance power consumption forecasting and smart grid analytics, concerns about privacy risks in electricity time\u2010series data have gained significant attention. Highlighting the unique characteristics of electricity data, such as its high periodicity and direct correlation with sensitive real\u2010world activities, this paper introduces a novel privacy auditing framework that systematically assesses the vulnerability of electricity forecasting models to gradient\u2010based data reconstruction attacks, where adversaries exploit model gradients to infer sensitive electricity usage data, posing a serious privacy risk to households, industries, and power operators. This paper introduces a novel privacy auditing framework that systematically assesses the vulnerability of electricity forecasting models to gradient\u2010based reconstruction attacks. Unlike traditional methods that primarily focus on privacy mitigation through model regularization or noise injection, our framework provides a quantitative evaluation of gradient leakage, allowing us to measure and analyze the extent to which adversaries can reconstruct private energy consumption data. Through experiments on benchmark electricity datasets (ETTh1, ETTh2, and ECL), we demonstrate that, without privacy\u2010preserving techniques, attackers can accurately reconstruct electricity consumption patterns, as indicated by the rapid decrease in mean squared error (MSE) during reconstruction iterations. However, the application of a standard defense mechanism, differential privacy (DP), significantly disrupts this process, increasing MSE and coefficient variance, thereby limiting an attacker's ability to recover meaningful energy consumption information. By formalizing the connection between gradient similarity and time\u2010series similarity, our study quantifies privacy risks in electricity forecasting models, and evaluates the effectiveness of DP as a representative defense mechanism. The main contribution is not an improvement to privacy\u2010preserving algorithms themselves, but rather the auditing framework used to measure their efficacy. Our analysis provides a quantitative framework for navigating the critical tradeoff between privacy preservation and model utility, while also considering the computational overhead of the auditing process. This work provides a systematic approach to privacy auditing, equipping researchers, policymakers, and energy providers with insights into the trade\u2010offs between model accuracy and data security. Future research should explore additional privacy\u2010preserving techniques such as homomorphic encryption, federated learning, and adversarial training to further enhance privacy protections in smart grid and energy forecasting applications.<\/jats:p>","DOI":"10.1002\/cpe.70398","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T03:40:08Z","timestamp":1764733208000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Auditing Privacy in Power Consumption Forecasting: Evaluating Gradient Leakage and Differential Privacy Defenses"],"prefix":"10.1002","volume":"38","author":[{"given":"Rixuan","family":"Qiu","sequence":"first","affiliation":[{"name":"Information and Telecommunication Branch State Grid Jiangxi Electric Power Company  Nanchang China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Luo","sequence":"additional","affiliation":[{"name":"Information and Telecommunication Branch State Grid Jiangxi Electric Power Company  Nanchang China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"He","sequence":"additional","affiliation":[{"name":"State Grid Jiangxi Electric Power Company  Nanchang China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Grid Jiangxi Electric Power Company  Nanchang China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuiping","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Information Engineering Nanchang Institute of Technology  Nanchang China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoping","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Information Engineering Nanchang Institute of Technology  Nanchang China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6643566"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3230685"},{"key":"e_1_2_10_4_1","first-page":"1291","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Salem A.","year":"2020"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833677"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"J.Hayes L.Melis G.Danezis andE.De Cristofaro \u201cLogan: Membership Inference Attacks Against Generative Models \u201darXiv Preprint arXiv:1705.07663 (2017).","DOI":"10.2478\/popets-2019-0008"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACOMP.2019.00022"},{"issue":"9","key":"e_1_2_10_10_1","first-page":"142","article-title":"Online Learning and Stochastic Approximations","volume":"17","author":"Bottou e. L.","year":"1998","journal-title":"Online Learning in Neural Networks"},{"key":"e_1_2_10_11_1","unstructured":"L.Zhu Z.Liu andS.Han \u201cDeep Leakage From Gradients \u201darXiv Preprint arXiv: 1906.08935 (2019)."},{"key":"e_1_2_10_12_1","unstructured":"B.Zhao K. R.Mopuri andH.Bilen \u201cIdlg: Improved Deep Leakage From Gradients \u201darXiv Preprint arXiv:2001.02610 (2020)."},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_2_10_15_1","unstructured":"J.Meng T.Huang H.Chen andC.Li \u201cIs Diffusion Model Safe? Severe Data Leakage via Gradient\u2010Guided Diffusion Model \u201darXiv Preprint arXiv:2406.09484 (2024)."},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796841"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103605"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03095-6_38"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01199"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T04:49:49Z","timestamp":1768193389000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70398"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/cpe.70398"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70398","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"assertion":[{"value":"2025-05-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70398"}}