{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T18:14:33Z","timestamp":1773339273962,"version":"3.50.1"},"reference-count":61,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Research and Graduate Studies at the University of Tabuk","award":["S-1444-0108"],"award-info":[{"award-number":["S-1444-0108"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      The generation of deepfake audio poses significant challenges to the reliability and security of automatic speaker verification (ASV)-based systems. ASV systems having applications in fintech, surveillance, home automation, security,\n                      <jats:italic>etc<\/jats:italic>\n                      ., are susceptible to a variety of deepfake\/voice cloning attacks, including speech synthesis and voice conversion (VC). Impostors launch audio deepfake attacks on ASV systems to compromise their security and cause financial losses, data breaches,\n                      <jats:italic>etc<\/jats:italic>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To combat such threats, we propose a robust and generalized audio deepfakes detection framework, DeepRawNet, by processing raw audio waveforms. Specifically, DeepRawNet is the enhanced version of RawNet2, introduces three key innovations: (1) we employ the Parametric Rectified Linear Unit (PReLU) activation in the residual blocks over Leaky ReLU in the RawNet2, introducing a learnable negative slope to enhance adaptive feature extraction, (2) substituting the simple convolution layer with a transpose convolution layer in the residual block addresses downsampling issues while preserving fine-grained temporal information crucial for capturing complex patterns in raw audio, (3) we incorporate the LogSoftmax activation function to stabilize and optimize learning during training and inference. These architectural refinements empower our DeepRawNet model with improved adaptability, robust learning capabilities, and enhanced capacity to capture complex temporal dependencies and discriminative patterns in the audio, making it a more effective solution for audio deepfake detection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We performed a rigorous evaluation of our proposed method on ASVspoof2019-LA and ASVspoof2021-LA\/DF datasets, including algorithm-wise and cross-corpora evaluation, an ablation study with different model configurations, and comparison against baseline models and existing approaches. Experimental results highlight the improved performance of DeepRawNet against the ASVspoof baselines, improved generalization across diverse spoofing attacks, particularly for the most challenging VC attacks, and effectiveness in combating deepfake audio threats.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj-cs.3670","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T08:12:25Z","timestamp":1773303145000},"page":"e3670","source":"Crossref","is-referenced-by-count":0,"title":["DeepRawNet: empowering deepfake audio detection through dynamic enhancements"],"prefix":"10.7717","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5062-9486","authenticated-orcid":true,"given":"Lubna A.","family":"Alharbi","sequence":"first","affiliation":[{"name":"Computer Science Department, University of Tabuk, Tabuk, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jasim","family":"Alnahas","sequence":"additional","affiliation":[{"name":"Industrial Engineering Department, University of Tabuk, Tabuk, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Javed","sequence":"additional","affiliation":[{"name":"James Watt School of Engineering, University of Glasgow, Glasgow, United Kingdom"},{"name":"Software Engineering Department, University of Engineering and Technology, Taxila, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0662-0185","authenticated-orcid":true,"given":"A\u2019aeshah","family":"Alhakamy","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Tabuk, Tabuk, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marriam","family":"Nawaz","sequence":"additional","affiliation":[{"name":"Software Engineering Department, University of Engineering and Technology, Taxila, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hafiz","family":"Malik","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Michigan, Dearborn, Michigan, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hafsa","family":"Ilyas","sequence":"additional","affiliation":[{"name":"Software Engineering Department, University of Engineering and Technology, Taxila, Punjab, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faris","family":"Alfaifi","sequence":"additional","affiliation":[{"name":"Industrial Engineering Department, University of Tabuk, Tabuk, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"10.7717\/peerj-cs.3670\/ref-1","doi-asserted-by":"publisher","first-page":"49265","DOI":"10.1109\/ACCESS.2022.3172954","article-title":"Robust speech emotion recognition using CNN+ LSTM based on stochastic fractal search optimization algorithm","volume":"10","author":"Abdelhamid","year":"2022","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3670\/ref-2","doi-asserted-by":"publisher","first-page":"20839","DOI":"10.1038\/s41598-025-04808-5","article-title":"DeepLASD countermeasure for logical access audio spoofing","volume":"15","author":"Al-Tairi","year":"2025","journal-title":"Scientific Reports"},{"issue":"5","key":"10.7717\/peerj-cs.3670\/ref-3","doi-asserted-by":"publisher","first-page":"155","DOI":"10.3390\/a15050155","article-title":"A review of modern audio deepfake detection methods: challenges and future directions","volume":"15","author":"Almutairi","year":"2022","journal-title":"Algorithms"},{"issue":"12","key":"10.7717\/peerj-cs.3670\/ref-4","doi-asserted-by":"publisher","first-page":"5128","DOI":"10.3390\/app14125128","article-title":"Using vocal-based emotions as a human error prevention system with convolutional neural networks","volume":"14","author":"Alsalhi","year":"2024","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3670\/ref-5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.17352","article-title":"AASIST3: KAN-enhanced AASIST speech deepfake detection using SSL features and additional regularization for the ASVspoof 2024 challenge","author":"Borodin","year":"2024"},{"key":"10.7717\/peerj-cs.3670\/ref-6","doi-asserted-by":"publisher","first-page":"100503","DOI":"10.1016\/j.mlwa.2023.100503","article-title":"Voice spoofing detection for multiclass attack classification using deep learning","volume":"14","author":"Boyd","year":"2023","journal-title":"Machine Learning with Applications"},{"issue":"6","key":"10.7717\/peerj-cs.3670\/ref-7","doi-asserted-by":"publisher","first-page":"8767","DOI":"10.1007\/s11042-021-11816-w","article-title":"Face recognition based on statistical features and SVM classifier","volume":"81","author":"Chaabane","year":"2022","journal-title":"Multimedia Tools and Applications"},{"issue":"1","key":"10.7717\/peerj-cs.3670\/ref-8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.12785\/ijcds\/1301111","article-title":"Spoof detection using sequentially integrated image and audio features","volume":"13","author":"Chakravarty","year":"2023","journal-title":"International Journal of Computing Digital Systems"},{"key":"10.7717\/peerj-cs.3670\/ref-9","doi-asserted-by":"publisher","first-page":"67443","DOI":"10.1007\/s11042-024-18217-9","article-title":"A lightweight feature extraction technique for deepfake audio detection","volume":"83","author":"Chakravarty","year":"2024","journal-title":"Multimedia Tools Applications"},{"key":"10.7717\/peerj-cs.3670\/ref-10","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2022.04.005","article-title":"A study on data augmentation in voice anti-spoofing","volume":"141","author":"Cohen","year":"2022","journal-title":"Speech Communication"},{"key":"10.7717\/peerj-cs.3670\/ref-11","doi-asserted-by":"crossref","DOI":"10.1109\/WIFS55849.2022.9975433","article-title":"Open challenges in synthetic speech detection","author":"Cuccovillo","year":"2022"},{"key":"10.7717\/peerj-cs.3670\/ref-12","first-page":"29","article-title":"Known-unknown data augmentation strategies for detection of logical access, physical access and speech deepfake attacks: ASVspoof 2021","author":"Das","year":"2021"},{"issue":"9","key":"10.7717\/peerj-cs.3670\/ref-13","doi-asserted-by":"publisher","first-page":"7300","DOI":"10.1016\/j.jksuci.2022.02.024","article-title":"A robust voice spoofing detection system using novel CLS-LBP features and LSTM","volume":"34","author":"Dawood","year":"2022","journal-title":"Journal of King Saud University-Computer Information Sciences"},{"key":"10.7717\/peerj-cs.3670\/ref-14","doi-asserted-by":"publisher","first-page":"101602","DOI":"10.1016\/j.csl.2023.101602","article-title":"Complementary regional energy features for spoofed speech detection","volume":"85","author":"Di\u015fken","year":"2024","journal-title":"Computer Speech Language"},{"key":"10.7717\/peerj-cs.3670\/ref-15","first-page":"29","article-title":"GAN discriminator-based audio deepfake detection","author":"Doan","year":"2023"},{"issue":"1","key":"10.7717\/peerj-cs.3670\/ref-16","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1080\/03772063.2024.2412799","article-title":"MelCochleaGram-DeepCNN: sequentially fused spectrogram and the DeepCNN classifiers-based audio spoof detection system","volume":"71","author":"Dua","year":"2025","journal-title":"IETE Journal of Research"},{"key":"10.7717\/peerj-cs.3670\/ref-17","first-page":"12531","article-title":"Spoofing attack augmentation: can differently-trained attack models improve generalisation?","author":"Ge","year":"2024"},{"key":"10.7717\/peerj-cs.3670\/ref-18","doi-asserted-by":"publisher","first-page":"37219","DOI":"10.1109\/ACCESS.2024.3374768","article-title":"Recognition of Arabic accents from English spoken speech using deep learning approach","volume":"12","author":"Habbash","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3670\/ref-19","doi-asserted-by":"publisher","first-page":"134018\u2013134028","DOI":"10.1109\/ACCESS.2022.3231480","article-title":"Deepfake audio detection via MFCC features using machine learning","volume":"10","author":"Hamza","year":"2022","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3670\/ref-20","doi-asserted-by":"publisher","first-page":"7152","DOI":"10.1109\/ACCESS.2020.3048839","article-title":"A multivocal literature review on growing social engineering based cyber-attacks\/threats during the COVID-19 pandemic: challenges and prospective solutions","volume":"9","author":"Hijji","year":"2021","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3670\/ref-21","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1109\/LSP.2021.3089437","article-title":"Towards end-to-end synthetic speech detection","volume":"28","author":"Hua","year":"2021","journal-title":"IEEE Signal Processing Letters"},{"key":"10.7717\/peerj-cs.3670\/ref-22","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49660.2025.10888328","article-title":"Generalizable audio deepfake detection via latent space refinement and augmentation","author":"Huang","year":"2025"},{"key":"10.7717\/peerj-cs.3670\/ref-23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.05614","article-title":"Self-attention and hybrid features for replay and deep-fake audio detection","author":"Huang","year":"2024"},{"key":"10.7717\/peerj-cs.3670\/ref-24","first-page":"70","article-title":"Deepfake audio detection via feature engineering and machine learning","author":"Iqbal","year":"2022"},{"key":"10.7717\/peerj-cs.3670\/ref-25","doi-asserted-by":"publisher","first-page":"116770","DOI":"10.1016\/j.eswa.2022.116770","article-title":"Voice spoofing detector: a unified anti-spoofing framework","volume":"198","author":"Javed","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3670\/ref-26","first-page":"6367","article-title":"AASIST: audio anti-spoofing using integrated spectro-temporal graph attention networks","author":"Jung","year":"2022"},{"key":"10.7717\/peerj-cs.3670\/ref-27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.08104","article-title":"RawNet: advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification","author":"Jung","year":"2019"},{"key":"10.7717\/peerj-cs.3670\/ref-28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.14642","article-title":"Practical attacks on voice spoofing countermeasures","author":"Kassis","year":"2021"},{"key":"10.7717\/peerj-cs.3670\/ref-29","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-2557691\/v1","article-title":"Voice spoofing attacks and countermeasures: a systematic review, analysis, and experimental evaluation","author":"Khan","year":"2023a","journal-title":"Research Square"},{"issue":"Suppl 1","key":"10.7717\/peerj-cs.3670\/ref-30","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/s10462-023-10539-8","article-title":"Battling voice spoofing: a review, comparative analysis, and generalizability evaluation of state-of-the-art voice spoofing counter measures","volume":"56","author":"Khan","year":"2023b","journal-title":"Artificial Intelligence Review"},{"key":"10.7717\/peerj-cs.3670\/ref-31","doi-asserted-by":"crossref","DOI":"10.21437\/ASVspoof.2024-13","article-title":"Exploring generalization to unseen audio data for spoofing: insights from SSL models","author":"Kulkarni","year":"2024"},{"key":"10.7717\/peerj-cs.3670\/ref-32","first-page":"1116","article-title":"Siamese convolutional neural network using gaussian probability feature for spoofing speech detection","author":"Lei","year":"2020"},{"key":"10.7717\/peerj-cs.3670\/ref-33","first-page":"6354","article-title":"Replay and synthetic speech detection with Res2Net architecture","author":"Li","year":"2021"},{"issue":"14","key":"10.7717\/peerj-cs.3670\/ref-34","doi-asserted-by":"publisher","first-page":"8488","DOI":"10.3390\/app13148488","article-title":"Voice deepfake detection using the self-supervised pre-training model HuBERT","volume":"13","author":"Li","year":"2023","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3670\/ref-35","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1109\/TASLP.2024.3358056","article-title":"Generalizing speaker verification for spoof awareness in the embedding space","volume":"32","author":"Liu","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech, Language Processing"},{"key":"10.7717\/peerj-cs.3670\/ref-36","doi-asserted-by":"publisher","first-page":"102257","DOI":"10.1016\/j.inffus.2024.102257","article-title":"Multi-space channel representation learning for mono-to-binaural conversion based audio deepfake detection","volume":"105","author":"Liu","year":"2024","journal-title":"Information Fusion"},{"key":"10.7717\/peerj-cs.3670\/ref-37","doi-asserted-by":"publisher","first-page":"102103","DOI":"10.1016\/j.inffus.2023.102103","article-title":"Generation and detection of manipulated multimodal audiovisual content: advances, trends and open challenges","volume":"103","author":"Liz-L\u00f3pez","year":"2024","journal-title":"Information Fusion"},{"key":"10.7717\/peerj-cs.3670\/ref-38","first-page":"6359","article-title":"A capsule network based approach for detection of audio spoofing attacks","author":"Luo","year":"2021"},{"key":"10.7717\/peerj-cs.3670\/ref-39","first-page":"1","article-title":"A lightweight and efficient model for audio anti-spoofing","author":"Ma","year":"2023"},{"issue":"4","key":"10.7717\/peerj-cs.3670\/ref-40","doi-asserted-by":"publisher","first-page":"3974","DOI":"10.1007\/s10489-022-03766-z","article-title":"Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward","volume":"53","author":"Masood","year":"2023","journal-title":"Applied Intelligence"},{"key":"10.7717\/peerj-cs.3670\/ref-41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.07564","article-title":"ALReLU: a different approach on leaky ReLU activation function to improve neural networks performance","author":"Mastromichalakis","year":"2020"},{"issue":"14","key":"10.7717\/peerj-cs.3670\/ref-42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-023-15329-6","article-title":"Texture analysis of edge mapped audio spectrogram for spoofing attack detection","volume":"83","author":"Meriem","year":"2023","journal-title":"Multimedia Tools Applications"},{"key":"10.7717\/peerj-cs.3670\/ref-43","doi-asserted-by":"publisher","first-page":"13073","DOI":"10.1007\/s11042-023-16127-w","article-title":"Optimized deep network based spoof detection in automatic speaker verification system","volume":"83","author":"Neelima","year":"2023","journal-title":"Multimedia Tools Applications"},{"key":"10.7717\/peerj-cs.3670\/ref-44","doi-asserted-by":"publisher","first-page":"94563","DOI":"10.1109\/ACCESS.2023.3310809","article-title":"On the defense of spoofing countermeasures against adversarial attacks","volume":"11","author":"Nguyen-Vu","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3670\/ref-45","first-page":"012156","article-title":"Research on image retrieval using deep convolutional neural network combining L1 regularization and PRelu activation function","volume":"69","author":"QingJie","year":"2017"},{"key":"10.7717\/peerj-cs.3670\/ref-46","article-title":"RawNet2 ASVspoof 2021 baseline","author":"RawNet2 Code","year":"2021"},{"key":"10.7717\/peerj-cs.3670\/ref-47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.01034","article-title":"Fusion of modulation spectrogram and SSL with multi-head attention for fake speech detection","author":"Rishith Sadashiv","year":"2025"},{"key":"10.7717\/peerj-cs.3670\/ref-48","doi-asserted-by":"publisher","first-page":"101599","DOI":"10.1016\/j.csl.2023.101599","article-title":"Improving self-supervised learning model for audio spoofing detection with layer-conditioned embedding fusion","volume":"86","author":"Sinha","year":"2024","journal-title":"Computer Speech Language"},{"key":"10.7717\/peerj-cs.3670\/ref-49","first-page":"10357","article-title":"Refining activation downsampling with SoftPool","author":"Stergiou","year":"2021"},{"key":"10.7717\/peerj-cs.3670\/ref-50","first-page":"6369","article-title":"End-to-end anti-spoofing with RawNet2","author":"Tak","year":"2021"},{"key":"10.7717\/peerj-cs.3670\/ref-51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.07725","article-title":"Investigating self-supervised front ends for speech spoofing countermeasures","author":"Wang","year":"2021"},{"key":"10.7717\/peerj-cs.3670\/ref-52","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10094779","article-title":"Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders","author":"Wang","year":"2023"},{"key":"10.7717\/peerj-cs.3670\/ref-53","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.neucom.2023.02.013","article-title":"Self-adaptive logit balancing for deep neural network robustness: defence and detection of adversarial attacks","volume":"531","author":"Wei","year":"2023","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3670\/ref-54","first-page":"19","article-title":"Audio deepfake detection based on a combination of F0 information and real plus imaginary spectrogram features","author":"Xue","year":"2022"},{"issue":"2","key":"10.7717\/peerj-cs.3670\/ref-55","doi-asserted-by":"publisher","first-page":"172318","DOI":"10.1007\/s11704-022-2121-6","article-title":"Physiological-physical feature fusion for automatic voice spoofing detection","volume":"17","author":"Xue","year":"2023","journal-title":"Frontiers of Computer Science"},{"key":"10.7717\/peerj-cs.3670\/ref-56","doi-asserted-by":"publisher","first-page":"104315","DOI":"10.1016\/j.dsp.2023.104315","article-title":"Integration of audio-visual information for multi-speaker multimedia speaker recognition","volume":"145","author":"Yang","year":"2024","journal-title":"Digital Signal Processing"},{"key":"10.7717\/peerj-cs.3670\/ref-57","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1109\/TASLP.2021.3060810","article-title":"Modified magnitude-phase spectrum information for spoofing detection","volume":"29","author":"Yang","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.7717\/peerj-cs.3670\/ref-58","first-page":"3799","article-title":"SMACK: semantically meaningful adversarial audio attack","author":"Yu","year":"2023"},{"key":"10.7717\/peerj-cs.3670\/ref-59","first-page":"11636","article-title":"Improving short utterance anti-spoofing with AASIST2","author":"Zhang","year":"2024"},{"issue":"7","key":"10.7717\/peerj-cs.3670\/ref-60","doi-asserted-by":"publisher","first-page":"317","DOI":"10.3390\/a16070317","article-title":"Audio anti-spoofing based on audio feature fusion","volume":"16","author":"Zhang","year":"2023","journal-title":"Algorithms"},{"issue":"1","key":"10.7717\/peerj-cs.3670\/ref-61","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13677-022-00306-5","article-title":"Voice spoofing countermeasure for voice replay attacks using deep learning","volume":"11","author":"Zhou","year":"2022","journal-title":"Journal of Cloud Computing"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3670.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3670.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3670.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3670.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T08:12:29Z","timestamp":1773303149000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":61,"alternative-id":["10.7717\/peerj-cs.3670"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3670","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]},"article-number":"e3670"}}