Signature verification using blockchain technology: a deep learning method using optimizer benchmarking
Ashish Kumar Srivastava1, Tauseef Ahmad2 and Md. Vaseem Naiyer1
Department of Information Technology,Rajkiya Engineering College, Azamgarh,Uttar Pradesh,India2
Corresponding Author : Tauseef Ahmad
Recieved : 25-August-2025; Revised : 09-January-2026; Accepted : 24-January-2026
Abstract
Offline handwritten signature verification is a vital biometric authentication task in financial and legal applications, where reliability, security, and auditability are essential. This paper presents a blockchain-enabled deep learning framework for offline signature verification that integrates a convolutional neural network (CNN) with immutable blockchain-based logging. An experimental comparison of four optimization algorithms stochastic gradient descent (SGD) with momentum, root mean square propagation (RMSprop), adaptive moment estimation (Adam), and adaptive moment estimation with decoupled weight decay (AdamW) is conducted on the Centre of Excellence for Document Analysis and Recognition (CEDAR) dataset. The performance is evaluated using accuracy, precision, recall, F1-score, receiver operating characteristic (ROC) curves, area under the curve (AUC), false acceptance rate (FAR), and false rejection rate (FRR). The experimental results show that Adam achieves the highest classification performance with 94.1% accuracy and a 93.2% F1-score, while RMSprop provides superior threshold discrimination, achieving the highest AUC of 0.573 and lowest equal error rate of 0.456. SGD with momentum exhibits stable but slower convergence, whereas AdamW performs poorly for this dataset. Additionally, blockchain-based logging ensures a tamper-proof and auditable recording of verification outcomes with less than 3% computational overhead. The proposed framework demonstrates that careful optimizer selection combined with blockchain integration can significantly enhance the reliability, transparency, and security of biometric signature verification systems.
Keywords
Blockchain, Deep learning, Optimizer benchmarking, Biometric authentication, Signature verification, Transparency.
Cite this article
Srivastava AK, Ahmad T, Naiyer M. Signature verification using blockchain technology: a deep learning method using optimizer benchmarking. International Journal of Advanced Computer Research. 2026;16(76):77-95. DOI : 10.19101/IJACR.2025.1570019
[1] Impedovo D, Pirlo G. Automatic signature verification: the state of the art. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews). 2008; 38(5):609-35.
[2] Impedovo D, Pirlo G, Plamondon R. Handwritten signature verification: new advancements and open issues. In international conference on frontiers in handwriting recognition 2012 (pp. 367-72). IEEE.
[3] Jain AK, Ross A, Prabhakar S. An introduction to biometric recognition. IEEE Transactions on Circuits and Systems for Video Technology. 2004; 14(1):4-20.
[4] Leclerc F, Plamondon R. Automatic signature verification: the state of the art—1989–1993. International Journal of Pattern Recognition and Artificial Intelligence. 1994; 8(3):643-60.
[5] Plamondon R, Lorette G. Automatic signature verification and writer identification-the state of the art. Pattern Recognition. 1989; 22(2):107-31.
[6] Plamondon R, Srihari SN. Online and off-line handwriting recognition: a comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002; 22(1):63-84.
[7] Hafemann LG, Sabourin R, Oliveira LS. Analyzing features learned for offline signature verification using deep CNNS. In 23rd international conference on pattern recognition (ICPR) 2016 (pp. 2989-94). IEEE.
[8] Berman DS, Buczak AL, Chavis JS, Corbett CL. A survey of deep learning methods for cyber security. Information. 2019; 10(4):122.
[9] Wang Q, Guo W, Zhang K, Ororbia AG, Xing X, Liu X, et al. Adversary resistant deep neural networks with an application to malware detection. In proceedings of the 23rd international conference on knowledge discovery and data mining 2017 (pp. 1145-53). ACM.
[10] Priyadarshini I. Introduction to blockchain technology. Cyber security in parallel and distributed computing: concepts, techniques, applications and case studies 2019 (pp. 91-107). Scrivener Publishing LLC.
[11] Hyla T, Pejaś J. Long-term verification of signatures based on a blockchain. Computers & Electrical Engineering. 2020; 81:106523.
[12] Zhou Z, Luo X, Bai Y, Wang X, Liu F, Liu G, et al. A scalable blockchain‐based integrity verification scheme. Wireless Communications and Mobile Computing. 2022; 2022(1):7830508.
[13] Selvakumari S, Durairaj M. A comparative study of optimization techniques in deep learning using the MNIST dataset. Indian Journal of Science and Technology. 2025; 18(10):803-10.
[14] Hong Y, Lin J. On convergence of adam for stochastic optimization under relaxed assumptions. Advances in Neural Information Processing Systems. 2024; 37:10827-77.
[15] Xiang Q, Wang X, Lei L, Song Y. Dynamic bound adaptive gradient methods with belief in observed gradients. Pattern Recognition. 2025; 168:111819.
[16] Barakat A, Bianchi P. Convergence rates of a momentum algorithm with bounded adaptive step size for nonconvex optimization. In Asian conference on machine learning 2020 (pp. 225-40). PMLR.
[17] Li H, Rakhlin A, Jadbabaie A. Convergence of adam under relaxed assumptions. Advances in Neural Information Processing Systems. 2023; 36:52166-96.
[18] Llugsi R, El YS, Fontaine A, Lupera P. Comparison between Adam, AdaMax and Adam W optimizers to implement a weather forecast based on neural networks for the Andean city of Quito. In fifth Ecuador technical chapters meeting (ETCM) 2021 (pp. 1-6). IEEE.
[19] Kokku SA, Telugu A, Kompelly S, Gundavarapu MR, Nimmala S. Performance analysis of deep learning approaches for offline signature verification. International Journal of Engineering and Advanced Technology. 2022; 11(4):94-9.
[20] Rokade S, Singh SK, Bansod S, Pal P. An offline signature verification using deep convolutional neural networks. In third international conference on advances in electrical, computing, communication and sustainable technologies (ICAECT) 2023 (pp. 1-4). IEEE.
[21] Jithendra B, Krishna CN, Manaswini KS. Offline based signature verification using deep neural networks. In 2nd international conference on edge computing and applications (ICECAA) 2023 (pp. 351-7). IEEE.
[22] Kad S, Darak M, Offline verification of signature using CNN. Journal of Emerging Technologies and Innovative Research. 2020;7(8):808-12.
[23] Blessy P, Kathiresan K, Yuvaraj N. Deep learning approach to offline signature forgery prevention. In 9th international conference on advanced computing and communication systems (ICACCS) 2023 (pp. 1570-5). IEEE.
[24] Sharma N, Gupta S, Mohamed HG, Anand D, Mazón JL, Gupta D, et al. Siamese convolutional neural network-based twin structure model for independent offline signature verification. Sustainability. 2022; 14(18):1-14.
[25] Kao HH, Wen CY. An offline signature verification and forgery detection method based on a single known sample and an explainable deep learning approach. Applied Sciences. 2020; 10(11):3716.
[26] Bhunia AK, Alaei A, Roy PP. Signature verification approach using fusion of hybrid texture features. Neural Computing and Applications. 2019; 31(12):8737-48.
[27] Drouhard JP, Sabourin R, Godbout M. A neural network approach to off-line signature verification using directional PDF. Pattern Recognition. 1996; 29(3):415-24.
[28] Roy S, Sarkar D, Malakar S, Sarkar R. Offline signature verification system: a graph neural network based approach. Journal of Ambient Intelligence and Humanized Computing. 2023; 14(7):8219-29.
[29] Li WH, Zhong Z, Zheng WS. One-pass person re-identification by sketch online discriminant analysis. Pattern Recognition. 2019; 93:237-50.
[30] Maergner P, Pondenkandath V, Alberti M, Liwicki M, Riesen K, Ingold R, et al. Combining graph edit distance and triplet networks for offline signature verification. Pattern Recognition Letters. 2019; 125:527-33.
[31] Su G, Shang Y, Du C, Wang J. A multimodal and multistage face recognition method for simulated portrait. In18th international conference on pattern recognition (ICPR'06) 2006 (pp. 1013-17). IEEE.
[32] Ren C, Zhang J, Wang H, Shen S. Vision graph convolutional network for writer-independent offline signature verification. In international joint conference on neural networks (IJCNN) 2023 (pp. 1-7). IEEE.
[33] Yli-huumo J, Ko D, Choi S, Park S, Smolander K. Where is current research on blockchain technology?-a systematic review. PloS One. 2016; 11(10):e0163477.
[34] Le TV, Hsu CL. A systematic literature review of blockchain technology: Security properties, applications and challenges. Journal of Internet Technology. 2021; 22(4):789-802.
[35] Shafay M, Ahmad RW, Salah K, Yaqoob I, Jayaraman R, Omar M. Blockchain for deep learning: review and open challenges. Cluster Computing. 2023; 26(1):197-221.
[36] Zhu X, Li H, Yu Y. Blockchain-based privacy preserving deep learning. In international conference on information security and cryptology 2018 (pp. 370-83). Cham: Springer International Publishing.
[37] Hamadene A, Chibani Y, Nemmour H. Off-line handwritten signature verification using contourlet transform and co-occurrence matrix. In international conference on frontiers in handwriting recognition 2012 (pp. 343-7). IEEE.
[38] Nemmour H, Chibani Y. Off-line signature verification using artificial immune recognition system. In international conference on electronics, computer and computation (ICECCO) 2013 (pp. 164-7). IEEE.
[39] Kamihira Y, Ohyama W, Wakabayashi T, Kimura F. Improvement of Japanese signature verification by combined segmentation verification approach. In 2nd IAPR Asian conference on pattern recognition 2013 (pp. 501-5). IEEE.
[40] Griechisch E, Malik MI, Liwicki M. Online signature verification based on kolmogorov-smirnov distribution distance. In 14th international conference on frontiers in handwriting recognition 2014 (pp. 738-42). IEEE.
[41] Fayyaz M, Saffar MH, Sabokrou M, Hoseini M, Fathy M. Online signature verification based on feature representation. In the international symposium on artificial intelligence and signal processing (AISP) 2015 (pp. 211-6). IEEE.
[42] Radhika KS, Gopika S. Online and offline signature verification: a combined approach. Procedia Computer Science. 2015; 46:1593-600.
[43] Lech M, Czyzewski A. A handwritten signature verification method employing a tablet. In signal processing: algorithms, architectures, arrangements, and applications (SPA) 2016 (pp. 45-50). IEEE.
[44] Hamadene A, Chibani Y. One-class writer-independent offline signature verification using feature dissimilarity thresholding. IEEE Transactions on Information Forensics and Security. 2016; 11(6):1226-38.
[45] Taşkiran M, Çam ZG. Offline signature identification via HOG features and artificial neural networks. In 15th international symposium on applied machine intelligence and informatics (SAMI) 2017 (pp. 83-6). IEEE.
[46] Suryani D, Irwansyah E, Chindra R. Offline signature recognition and verification system using efficient fuzzy kohonen clustering network (EFKCN) algorithm. Procedia computer science. 2017; 116:621-8.
[47] Serdouk Y, Nemmour H, Chibani Y. New histogram-based descriptor for off-line handwritten signature verification. In 15th international conference on computer systems and applications (AICCSA) 2018 (pp. 1-5). IEEE.
[48] Sharif M, Khan MA, Faisal M, Yasmin M, Fernandes SL. A framework for offline signature verification system: best features selection approach. Pattern Recognition Letters. 2020; 139:50-9.
[49] Antal M, Szabó LZ, Tordai T. Online signature verification on MOBISIG finger‐drawn signature corpus. Mobile Information Systems. 2018; 2018(1):1-15.
[50] Jia Y, Huang L, Chen H. A two-stage method for online signature verification using shape contexts and function features. Sensors. 2019; 19(8):1-17.
[51] Mersa O, Etaati F, Masoudnia S, Araabi BN. Learning representations from persian handwriting for offline signature verification, a deep transfer learning approach. In 4th international conference on pattern recognition and image analysis (IPRIA) 2019 (pp. 268-73). IEEE.
[52] Saleem M, Kovari B. Online signature verification based on signer dependent sampling frequency and dynamic time warping. In 7th international conference on soft computing & machine intelligence (ISCMI) 2020 (pp. 182-6). IEEE.
[53] https://www.kaggle.com/datasets/shreelakshmigp/cedardataset. Accessed 24 December 2025.
[54] Zhang H, Guo J, Li K, Zhang Y, Zhao Y. Offline signature verification based on feature disentangling aided variational autoencoder. In 5th international conference on machine learning and computer application (ICMLCA) 2024 (pp. 549-54). IEEE.
[55] Tehsin S, Hassan A, Riaz F. Ensemble learning for offline signature verification using fused deep features. In 5th international conference on advancements in computational sciences (ICACS) 2024 (pp. 1-6). IEEE.
[56] Kumar GM, Satyanarayana P, Sridhar B, Rohith KT, Rao GP, Krishnan VG. Deep neural networks based handwritten signature verification using machine learning algorithms. In Asian conference on intelligent technologies (ACOIT) 2024 (pp. 1-6). IEEE.
[57] SP AJ, Balaji B. Advanced deep learning algorithm for offline signature fraud detection. In 9th international conference on communication and electronics systems (ICCES) 2024 (pp. 2110-15). IEEE.
[58] Alsuhimat FM, Mohamad FS. A hybrid method of feature extraction for signatures verification using CNN and HOG a multi-classification approach. IEEE Access. 2023; 11:21873-82.
[59] Emberi NB, Mohan A, Naphade CA, Ransing R. Harnessing deep neural networks for accurate offline signature forgery detection. In 7th international conference on intelligent computing and control systems (ICICCS) 2023 (pp. 619-26). IEEE.
[60] Zois EN, Tsourounis D, Kalivas D. Similarity distance learning on SPD manifold for writer independent offline signature verification. IEEE Transactions on Information Forensics and Security. 2023; 19:1342-56.
[61] Wang Z, Muhammat M, Yadikar N, Aysa A, Ubul K. Advances in offline handwritten signature recognition research: a review. IEEE Access. 2023; 11:120222-36.
[62] Kazi A, Bharadi V, Prasad K. Attention-driven CNN-LSTM hybrid models for secure dynamic signature verification. In 3rd international conference on communication, security, and artificial intelligence (ICCSAI) 2025 (pp. 2041-7). IEEE.
[63] Akter T, Akter MS, Mahmud T, Chakma R, Hossain MS, Andersson K. Evaluating the performance of machine learning models in handwritten signature verification. In Asia Pacific conference on innovation in technology (APCIT) 2024 (pp. 1-6). IEEE.