1. A secure electronic voting system comprising: a voter interface (105) accessed by a voter to provide a plurality of authentication factors including at least one biometric factor and one knowledge-based factor, for verifying eligibility to vote; an AI module (110) communicatively coupled to the voter interface (105), to detect and prevent spoofing or fraudulent authentication attempts using artificial intelligence applied to biometric input; an authentication module (115) to verify identity of the voter using at least two authentication factors from the plurality of authentication factors, wherein a plurality of voting options are displayed over the voter interface (105) upon successful authentication of the voter; a vote registration unit (120) to generate a unique vote transaction for each vote cast by the authenticated voter, wherein the vote transaction is anonymized and securely recorded, timestamped, and immutably stored on a distributed ledger maintained by a permissioned blockchain network; an administrative dashboard (125), accessed by authorized election administrators to monitor voting metrics and audit voting records without accessing voter identities, wherein the system ensures end-to-end vote integrity, anonymity, and verifiability while preventing unauthorized access and duplicate voting.

2. The system as claimed in claim 1, wherein the biometric factor comprises at least one of iris recognition, facial recognition, fingerprint scanning, or voice recognition.

3. The system as claimed in claim 1, wherein the knowledge-based factor comprises a password, PIN, or security question.

4. The system as claimed claim 1, wherein the AI module (110) employs machine learning protocols to continuously improve spoof detection accuracy based on voter input patterns.

5. The system as claimed claim 1, wherein the vote registration unit (120) generates a cryptographic hash of each vote transaction prior to storage on the blockchain ledger.

6. The system as claimed claim 1, wherein the distributed ledger is implemented using Hyperledger Fabric to support permissioned access control and modular consensus mechanisms.

7. The system as claimed claim 1, wherein the administrative dashboard (125) comprises a visual analytics interface to display real-time voting metrics, node activity, and system alerts.

8. The system as claimed claim 1, wherein the voter interface (105) is accessible through a secure mobile application or a web-based portal with end-to-end encryption.

9. The system as claimed claim 1, wherein the system performs automated checks to prevent duplicate voting by linking voter authentication history with blockchain-stored vote transactions.

10. A method for securely conducting electronic voting using a secure electronic voting system (100), the method comprising: receiving, via a voter interface (105), a plurality of authentication factors from a voter; analyzing, using an AI module (110), the biometric factor to detect and prevent spoofing or fraudulent attempts during authentication; verifying, by an authentication module (115), the identity of the voter based on at least two of the received authentication factors; displaying, upon successful verification, a plurality of voting options to the authenticated voter via the voter interface (105); registering a vote cast by the authenticated voter, by generating a unique vote transaction; anonymizing and recording the vote transaction, and securely timestamping and immutably storing the transaction on a distributed ledger maintained by a permissioned blockchain network; and providing, through an administrative dashboard (125), access to voting metrics and audit records to authorized election administrators without exposing voter identities.

Description:FIELD OF THE INVENTION
[0001] The present invention relates to the field of electronic voting systems, and more specifically to a secure electronic voting system that utilizes multi-factor authentication to ensure the integrity, anonymity, and verifiability of votes cast during an election.

BACKGROUND OF THE INVENTION
[0002] The process of conducting elections plays a vital role in the functioning of democratic societies, providing a mechanism for citizens to choose their representatives and influence governance. Traditionally, voting has been conducted using paper ballots and manual counting, which, while reliable, can be labor-intensive, slow, and susceptible to human error. As societies have become more digitally connected, there has been a growing interest in transitioning to electronic voting systems to enhance efficiency and accessibility.
[0003] Despite the advantages offered by electronic voting, significant challenges persist in ensuring the security, privacy, and integrity of the voting process. One primary concern is the accurate verification of voter identity to prevent fraudulent activities such as impersonation or duplicate voting. At the same time, it is critical to maintain voter anonymity and protect personal data to uphold the confidentiality of individual votes.
[0004] Moreover, ensuring that votes are recorded accurately and are tamper-proof is essential to preserve trust in electoral outcomes. Many conventional electronic voting solutions lack sufficient mechanisms to prevent unauthorized access or manipulation of voting data, raising doubts about their reliability and transparency. Additionally, auditability the ability to independently verify and validate the correctness of the election results remains a challenge in many existing systems.
[0005] The balance between accessibility, security, and transparency is further complicated by the diverse technological capabilities and resources of different electoral environments. Therefore, there is a pressing need for advancements that address these multifaceted challenges comprehensively.
[0006] Several approaches have been proposed in the prior art, aiming to enhance voter authentication, improve data security, and provide verifiable record-keeping. However, these approaches often face limitations, including complexity of implementation, scalability issues, or insufficient protection against evolving cyber threats.
[0007] Accordingly, there exists a continuing demand for an improved electronic voting solution that can ensure robust security and privacy measures, facilitate accurate and reliable vote recording, and support transparent auditing, all while remaining accessible and user-friendly for a broad range of voters.

OBJECT AND SUMMARY OF THE INVENTION
[0008] In view of the foregoing disadvantages inherent in the prior art, the general purpose of the present disclosure is to provide a multimodal authentication system and a method thereof, to include all advantages of the prior art, and to overcome the drawbacks inherent in the prior art.
[0009] Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
[0010] An object of the present disclosure is to ameliorate one or more problems of the prior art or to at least provide a useful alternative. An object of the present disclosure is to provide a secure electronic voting system and a method thereof.
[0011] Another object of the present disclosure is to provide a secure and tamper-resistant electronic voting system that enhances voter trust and system transparency during the electoral process
[0012] Another object of the present disclosure is to prevent fraudulent access or impersonation attempts during the voter authentication process by employing advanced detection techniques based on artificial intelligence.
[0013] Yet another object of the present disclosure is to ensure that once a vote is cast, it is anonymized, time-stamped, and recorded in a manner that is immutable, traceable, and resistant to tampering or alteration.
[0014] Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
[0015] The secure electronic voting system of the present disclosure comprises a voter interface through which eligible users may access the voting platform and undergo a series of authentication steps prior to being allowed to cast their vote. The present system utilizes multiple authentication factors, which must be presented by the voter before casting a vote. These authentication factors include at least one biometric factor such as facial recognition, iris scanning, fingerprint detection, or voice authentication and one knowledge-based factor, such as a password, PIN, or a security question. This multi-factor approach ensures that only authorized and eligible individuals can access the voting interface, significantly reducing the possibility of impersonation or unauthorized access.
[0016] To further strengthen the authentication process, the system incorporates an AI module that is communicatively coupled to the voter interface. This module is configured to analyze biometric data inputs using machine learning algorithms to detect and prevent spoofing attempts, such as the use of static images, pre-recorded audio, or artificial fingerprints. The AI module is capable of improving its detection capabilities over time through adaptive learning based on voter input patterns and previously identified fraudulent behaviors.
[0017] Upon successful verification of a voter’s identity, the system displays a secure ballot interface that allows the authenticated voter to make their selections from a list of eligible voting options. The interface may be accessed via secure devices such as mobile applications or encrypted web-based portals, providing flexibility in how voters interact with the system while maintaining strong security controls. End-to-end encryption is employed to protect all data transmissions between the client interface and the backend system.
[0018] Once a vote is cast, a vote registration unit generates a unique, anonymized vote transaction. This vote transaction is cryptographically hashed to ensure data integrity, timestamped to establish chronological order, and stored immutably on a distributed ledger maintained by a permissioned blockchain network. The use of permissioned blockchain such as Hyperledger Fabric allows the system to implement access controls, consensus mechanisms, and modular governance while protecting the anonymity of individual voters.
[0019] The permissioned blockchain ensures that every recorded vote is verifiable yet cannot be altered or deleted, thereby preventing tampering or ballot stuffing. The anonymity of each voter is preserved throughout the process, and each vote is decoupled from personally identifiable information. This ensures that while the vote itself can be audited and traced through the ledger for verification, the identity of the voter remains confidential and inaccessible to both internal and external entities.
[0020] To provide election authorities with the necessary tools for oversight, the system features an administrative dashboard accessible only to authorized personnel. This dashboard enables real-time monitoring of the voting process, including metrics such as voter turnout, system activity, and node performance across the distributed ledger. Importantly, the dashboard is designed to maintain strict voter privacy by only exposing anonymized and aggregated data. It also allows administrators to perform integrity checks, review audit trails, and receive alerts on suspicious activity.
[0021] Additionally, the system includes functionality to detect and prevent duplicate voting. This is achieved by linking a voter’s authentication history with the vote transaction record on the blockchain, ensuring that each voter is only permitted to vote once during the designated voting period. The system automatically performs consistency checks between submitted authentication data and stored vote transactions, flagging or rejecting repeated attempts to vote.
[0022] In an aspect of the present dislcousre, a method for conducting secure electronic voting by a secure electronic voting system begins with receiving, via a voter interface, at least one biometric and one knowledge-based authentication factor from a voter. Next, the AI module analyzes the biometric factor to prevent spoofing. The authentication module then verifies the voter’s identity using the submitted authentication factors. Upon successful verification, voting options are displayed to the voter. The voter’s selection is used to generate a unique vote transaction, which is then anonymized, timestamped, and stored immutably on a permissioned blockchain ledger. Election administrators subsequently access real-time analytics and audit logs via a secure dashboard, ensuring vote integrity, transparency, and auditability throughout the process.

BRIEF DESCRIPTION OF DRAWING
[0023] The foregoing summary, as well as the following detailed description of various embodiments, is better understood when read in conjunction with the drawings provided herein. For the purposes of illustration, there are shown in the drawings exemplary embodiments; however, the presently disclosed subject matter is not limited to the specific methods and instrumentalities disclosed.
[0024] Figure 1 illustrates a block diagram of a secure electronic voting system;
[0025] Figure 2 illustrates a flow chart depict5ing working of a secure electronic voting system; and
[0026] Figure 3 illustrates a flow chart for registering of a voter with different demographics as disclosed in the present disclosure;
[0027] Like reference numerals refer to like parts throughout the description of several views of the drawing.

DETAILED DESCRIPTION OF THE INVENTION
[0028] Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well- known apparatus structures, and well-known techniques are not described in detail.
[0029] The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a," "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "comprises," "comprising," "including," and "having," are open-ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, modules, units and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
[0030] The following detailed description should be read with reference to the drawings, in which similar elements in different drawings are identified with the same reference numbers. The drawings, which are not necessarily to scale, depict illustrative embodiments and are not intended to limit the scope of the disclosure.
[0031] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. In this application, the use of the singular includes the plural, the word "a" or "an" means "at least one", and the use of "or" means "and/or", unless specifically stated otherwise. Furthermore, the use of the term "including", as well as other forms, such as "includes" and "included", is not limiting. Also, terms such as "element" or "component" encompass both elements and components comprising one unit and elements or components that comprise more than one unit unless specifically stated otherwise.
[0032] Furthermore, the term “module”, as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions, written in a programming language, such as, Java, C, C++, python, or assembly. One or more software instructions in the modules can be embedded in firmware, such as in an EPROM. The modules described herein can be implemented as either software and/or hardware modules and can be stored in any type of non-transitory computer-readable medium or other storage device. Some non-limiting examples of non-transitory computer-readable media include CDs, DVDs, BLU-RAY, flash memory, and hard disk drives.
[0033] As illustrated in Figure 1 and 2, the secure electronic voting system (100) disclosed in the present disclosure includes a voter interface (105) that collects sequentially a plurality of authentication factors. The authentication factors include at least one biometric factor and at least one knowledge-based factor. Illustratively, the biometric factor may be an iris scan captured by a camera operating, a facial photograph captured under both visible-light and short-wave infrared spectra to frustrate two-dimensional photographic spoofs, a voice sample reciting a randomly generated pass-phrase, and/or a capacitive fingerprint image. Each raw biometric sample is pre-processed locally to remove background noise, equalise contrast, detect facial landmarks, or isolate iris rings. The pre-processing protocols apply adaptive histogram equalisation, unsharp-mask filtering, and wavelet de-noising so that illumination variance between devices does not induce excessive intra-class dispersion. The normalised biometric vector is then converted to template and subjected to hashing combined with a cryptographically secure random salt. The salt itself is encrypted with the enclave’s public key and stored off-chain in a dedicated key-value store whose access is restricted to an AI module (110). The AI module (110) is communicatively coupled to the voter interface (105). By separating the salt from the hash and confining cryptographic operations to the enclave, any subsequent breach of the cloud layer cannot invert the template back to an image, thereby satisfying data-minimisation mandates.
[0034] In case, the voter is new, for registering the new voter involves a sequence of secure and verifiable steps. Initially, the user accesses the system through the voter interface (105) and selects the registration option. The system prompts the user to input personal details such as name, government-issued voter ID, date of birth, and address. These credentials are then validated against an authorized electoral database to confirm eligibility. Upon successful validation, the system initiates a multi-factor authentication setup, wherein the voter must provide at least one biometric input (e.g., facial scan or iris scan) and one knowledge-based factor (e.g., password or PIN). The biometric input is further analyzed by an AI-based spoof detection module to ensure authenticity. After authentication, the system generates a cryptographic key pair and assigns a pseudonymous voter ID (PVID), which is hashed and immutably recorded on the permissioned blockchain. A confirmation receipt is then issued to the voter, completing the registration process and enabling secure participation in the election.
[0035] Parallel to biometric acquisition, the interface requests a knowledge-based factor typically a six-to-eight-character alphanumeric PIN, password or a security question. The knowledge based factor is passed through a password-strength meter to discourage dictionary words and personal dates. The PIN is salted, iterated with time and memory parameters chosen to defeat GPU-accelerated cracking rigs, and transmitted to an authentication module (115). The authentication module (115) is coupled to the AI module (110). Optionally, the voter may enrol a credential bound to a platform authenticator; such a credential gives the system a possession factor anchored in hardware and enables passwordless flows in subsequent elections while still maintaining the requisite cardinality of at least two factors.
[0036] Upon arrival at the server edge the biometric template, salt, hash, public key, and metadata indicating firmware version, geo-location co-ordinates, and device-integrity attestation are received by the artificial-intelligence (AI) module. The AI module (110) executes a deep-learning inference pipeline composed of successive convolutional, residual, and attention layers when performing facial spoof detection, or a gated recurrent unit when analysing speech. The models are pre-trained on a corpus exceeding one million bona-fide and spoofed samples, with class balancing, focal-loss regularisation, and defensive distillation to counter adversarial perturbations. Each incoming sample is scored with a numeric spoof-probability. If the score exceeds a threshold determined by equal-error-rate convergence tests, the session is flagged, rate-limited, and optionally subjected to an interactive challenge such as head-pose variation, eye-blink synchrony, or liveness-audio prompting. If the sample passes, the AI module (110) emits a signed Token embedding the spoof-score, a unique session identifier, and a non-correlatable pseudonymous voter digest (DV-ID) that is generated by expansion of the salt plus a secure key stored only inside a cluster.
[0037] The authentication module (115) receives the token and cross-checks the DV-ID against a relational index of active voters stored in a database. Where the election authority imposes constituency-based or time-window restrictions, an attribute-based access-control (ABAC) policy engine evaluates declarative rules that include zone-id, electoral phase, device trust-level, and the real-time health of blockchain validator nodes. Only if every rule evaluates to “permit” does the authentication module (115) signal the voter interface (105) to render the ballot. Rendering is governed by a deterministic front-end engine that serialises the candidate list based on server-provided identifiers and re-calculates a checksum to detect tampering with the Document-Object Model. Immediately upon display, the checksum is transmitted back to the server and compared against the canonical checksum for that constituency, mismatches trigger ballot invalidation and an incident report.
[0038] When the voter activates a ballot choice, the client-side application constructs a vote payload that comprises: (i) the candidate identifier; (ii) the election identifier; (iii) a monotonic timestamp to millisecond precision; (iv) the DV-ID; (v) the device-public-key fingerprint; and (vi) an optional zero-knowledge proof establishing, without revealing the DV-ID, that the voter is entitled to participate and has not already cast a ballot in the same election. The entire vote payload is symmetrically encrypted using an AES-256 key derived from an Elliptic-Curve Diffie-Hellman exchange between the enclave and a blockchain-gateway micro-service. The AES key is session-scoped, rotated after each ballot, and discarded from memory once the encryption completes.
[0039] The encrypted payload is passed to a vote-registration unit coupled to the authentication module (115). The vote registration unit (120) generates a Universally Unique Identifier (UUID-v4) as the vote transaction id and derives a content hash (H1) by the ciphertext. Optionally, a second hash (H2) is generated from the plaintext candidate id plus timestamp for internal analytics, H2 is never written on-chain. To protect against vote-buying coercion the vote-registration unit splits an elliptic-curve private key into two-of-three Shamir-Secret-Sharing shards: one shard resides in the enclave, a second in the HSM cluster, and a third with a supervising election-observer node. During commit, any two shards recombine to sign the transaction, thereby proving behaviour of both the voter device and at least one supervisory entity while withholding unilateral control from either.
[0040] Subsequently, the signed transaction is transmitted to a permissioned-blockchain network. In the reference implementation, the network comprises an ordering-service cluster running the Raft consensus algorithm and a set of peer nodes distributed across data-centres in no fewer than three availability zones. The endorsement policy requires an affirmative signature from at least one peer controlled by the Election Commission and one peer controlled by an accredited observer consortium, guaranteeing Byzantine fault tolerance up to f = (n − 1)/2 node failures. Hyperledger Fabric’s channel abstraction is employed so that votes pertaining to one constituency are segregated from another; nevertheless, a global system-channel records cryptographic digests of each block header, permitting cross-channel audit reconciliation without revealing ballot content.
[0041] Once the ordering service writes the block header to disk, a block-commit event is emitted through Fabric’s event-hub mechanism. The voter interface (105), having subscribed to this event via a server-sent-events stream, receives a confirmation that includes the block-hash and transaction index. The interface then displays a success screen and silently saves a receipt consisting of (i) the block-hash, (ii) the transaction UUID, (iii) a Merkle-path from the transaction hash to the block-root, and (iv) a timestamp issued by a compliant Time-Stamp Authority. As the receipt lacks the plaintext ballot choice, possession of the receipt cannot be used to prove how the voter cast her vote, thereby preserving coercion resistance.
[0042] Moreover, an administrative dashboard (125) communicatively coupled to the vote-registration unit. The dashboard queries the ledger, presents aggregated metrics turn-out percentages, block-finality latencies, peer endorsement latencies, and AI-flagged spoof incidents in real time. Drill-down screens allow election administrators to inspect specific transaction metadata but don’t expose raw DV-IDs or decrypted ballot contents. Audit-trail logs are themselves hashed hourly and pinned to a public blockchain such as Ethereum main-net or Polygon, creating an immutable cross-chain notarisation that external observers can verify independently.
[0043] At the close of the election, the peer nodes execute tallying chain-code that iterates deterministically over each vote transaction, decrypts the candidate identifier by invoking a threshold-decryption protocol again requiring multiple shards and increments vote counts accordingly. Because the decryption occurs inside Docker containers running on validator peers, and because all decryption calls are logged on-chain with cryptographic proofs, auditors may later reproduce the count by replaying the ledger in a sandbox environment. Any attempt to insert, delete, or reorder transactions would break the Merkle root and fail reproducibility checks.
[0044] Security posture is further reinforced through layered defences: (i) Web-Application Firewalls block injection and cross-site scripting attacks; (ii) Distributed-Denial-of-Service scrubbing centres absorb volumetric floods; (iii) continuous-integration pipelines run static-code analysis and container-image scanning; (iv) runtime intrusion-detection agents monitor kernel-level syscalls for anomaly signatures; and (v) all secrets—database passwords, API tokens—are rotated by a secrets-manager that enforces a maximum-lifetime policy.
[0045] In an alternative embodiment of the present disclosure, the system may include contemplate edge-deployment scenarios for remote or low-bandwidth regions. In such cases a compact “mini-peer” may be hosted on a portable single-board computer powered by solar panels. The mini-peer caches encrypted transactions locally and opportunistically synchronises with the global ordering service when connectivity resumes, utilising an asynchronous Byzantine agreement protocol to reconcile forks.
[0046] In an aspect of the present disclosure, a method for securely conducting electronic voting using the secure electronic voting system (100) includes a voter interface (105) accessed by a voter, the voter interface (105) may be provided via a secure mobile application or a web-based portal equipped with end-to-end encryption. Upon accessing the interface, the voter is prompted to provide a plurality of authentication factors, including at least one biometric factor such as iris scan, facial recognition, fingerprint scan, or voice authentication—and one knowledge-based factor such as a password, PIN, or response to a security question. The AI module (110), communicatively coupled to the interface, analyzes the biometric input to detect and prevent spoofing or fraudulent authentication attempts by applying machine learning algorithms trained on spoofing datasets and real-time biometric patterns. Once the authentication module (115) receives the authentication inputs, it verifies the voter’s identity based on at least two of the submitted factors. Upon successful verification, the system presents the voter with a list of available voting options through the interface.
[0047] The voter then casts a vote by selecting a preferred candidate or ballot option. The system registers the vote through the vote registration unit (120), which generates a unique vote transaction corresponding to the cast vote. The transaction is anonymized by dissociating voter identity from vote data and applying cryptographic hashing. The anonymized vote transaction is then securely timestamped and immutably stored on a distributed ledger maintained by a permissioned blockchain network, such as Hyperledger Fabric. This ledger ensures tamper-proof and transparent storage of vote data. Simultaneously, the system performs checks to prevent duplicate voting by correlating the voter’s authentication history with existing vote records.
[0048] Election administrators access an administrative dashboard (125) through secure authentication protocols. This dashboard enables monitoring of voting activity, node participation, vote counts, and system status in real-time. Importantly, the dashboard does not expose individual voter identities, thereby preserving voter anonymity. The method ensures end-to-end integrity, transparency, and verifiability of the election process while safeguarding against unauthorized access, identity spoofing, and multiple voting.
[0049] In one exemplary embodiment of the present disclosure, the present system incorporates a structured and inclusive registration and biometric verification workflow to accommodate a wide range of voter demographics. As depicted in the Figure 3, the process initiates with a general registration step. Upon registration, voters are categorized based on their status: out-of-station individuals, persons with disabilities, and senior citizens. Out-of-station applicants are further classified into students and working professionals, both of whom are required to furnish valid job or student identification proofs. Persons with disabilities must provide officially issued disability certificates, while senior citizens are required to submit valid birth certificates to validate their age and eligibility. All applicants, regardless of category, proceed to an authentication approval step where their submitted documents and identity credentials undergo verification. This stage may include biometric authentication and supporting documentation validation. If the authentication is successful, a unique voter ID is generated and granted to the applicant, marking the completion of the registration process as explained above in an embodiment of the present disclosure. In case of failed authentication, the application is rejected or returned for corrections, maintaining the integrity of the voter registry. This workflow ensures that all categories of voters, including remote, elderly, and disabled individuals, are accommodated within a secure, verifiable, and streamlined registration framework.
[0050] While considerable emphasis has been placed herein on the specific features of the preferred embodiment, it will be appreciated that many additional features can be added and that many changes can be made in the preferred embodiment without departing from the principles of the disclosure. These and other changes in the preferred embodiment of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.
[0051] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements.
[0052] The embodiments described above are intended only to illustrate and teach one or more ways of practicing or implementing the present invention, not to restrict its breadth or scope. The actual scope of the invention, which embraces all ways of practicing or implementing the teachings of the invention, is defined only by the following claims and their equivalents.

LIST OF REFERENCE NUMERALS
100 - Secure electronic voting system
105 - Voter interface
110 - AI module
115 - Authentication module
120 - Vote registration unit
125 - Administrative dashboard
, Claims:We Claim:
1. A secure electronic voting system comprising:
a voter interface (105) accessed by a voter to provide a plurality of authentication factors including at least one biometric factor and one knowledge-based factor, for verifying eligibility to vote;
an AI module (110) communicatively coupled to the voter interface (105), to detect and prevent spoofing or fraudulent authentication attempts using artificial intelligence applied to biometric input;
an authentication module (115) to verify identity of the voter using at least two authentication factors from the plurality of authentication factors,
wherein a plurality of voting options are displayed over the voter interface (105) upon successful authentication of the voter;
a vote registration unit (120) to generate a unique vote transaction for each vote cast by the authenticated voter,
wherein the vote transaction is anonymized and securely recorded, timestamped, and immutably stored on a distributed ledger maintained by a permissioned blockchain network;
an administrative dashboard (125), accessed by authorized election administrators to monitor voting metrics and audit voting records without accessing voter identities,
wherein the system ensures end-to-end vote integrity, anonymity, and verifiability while preventing unauthorized access and duplicate voting.

2. The system as claimed in claim 1, wherein the biometric factor comprises at least one of iris recognition, facial recognition, fingerprint scanning, or voice recognition.

3. The system as claimed in claim 1, wherein the knowledge-based factor comprises a password, PIN, or security question.
4. The system as claimed claim 1, wherein the AI module (110) employs machine learning protocols to continuously improve spoof detection accuracy based on voter input patterns.

5. The system as claimed claim 1, wherein the vote registration unit (120) generates a cryptographic hash of each vote transaction prior to storage on the blockchain ledger.
6. The system as claimed claim 1, wherein the distributed ledger is implemented using Hyperledger Fabric to support permissioned access control and modular consensus mechanisms.

7. The system as claimed claim 1, wherein the administrative dashboard (125) comprises a visual analytics interface to display real-time voting metrics, node activity, and system alerts.

8. The system as claimed claim 1, wherein the voter interface (105) is accessible through a secure mobile application or a web-based portal with end-to-end encryption.

9. The system as claimed claim 1, wherein the system performs automated checks to prevent duplicate voting by linking voter authentication history with blockchain-stored vote transactions.

10. A method for securely conducting electronic voting using a secure electronic voting system (100), the method comprising:
receiving, via a voter interface (105), a plurality of authentication factors from a voter;
analyzing, using an AI module (110), the biometric factor to detect and prevent spoofing or fraudulent attempts during authentication;
verifying, by an authentication module (115), the identity of the voter based on at least two of the received authentication factors;
displaying, upon successful verification, a plurality of voting options to the authenticated voter via the voter interface (105);
registering a vote cast by the authenticated voter, by generating a unique vote transaction;
anonymizing and recording the vote transaction, and securely timestamping and immutably storing the transaction on a distributed ledger maintained by a permissioned blockchain network; and
providing, through an administrative dashboard (125), access to voting metrics and audit records to authorized election administrators without exposing voter identities.