DecodeX
Home/Problem Statements/SIH26104
All 226 Statements
SIH26104SoftwareBlockchain & Cybersecurity
₹1,50,000 Prize (₹75k Joint)
•
Deadline: 20 September 2026
•
Submitted Ideas: 0/500

AI-Powered Real-Time Detection and Prevention of Voice Cloning Impersonation Attacks

Ministry / Organization: All India Council for Technical Education (AICTE)
Department: Cyber Security Cell
SIH Official Portal
Technical Complexity
8/10
Dataset Accessibility
7/10
36h Hackathon Viability
9/10
Step 0 • Zero-Jargon Layman Summary

“Hackers are using AI to perfectly mimic the voices of bosses and officials to trick employees into sending money. We need to build a digital 'lie detector' that listens to phone calls in real-time and warns users if the person on the other end is a computer-generated fake.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

A real-time voice integrity verification platform that acts as a middleware between communication channels (VoIP/Telecom) and the end-user to flag synthetic audio.

Step 2

WHO IS IT FOR?

Primary beneficiaries are banks, government departments, and corporate enterprises. Users include frontline employees, IT security teams, and high-net-worth individuals.

Step 3

WHY DOES IT EXIST?

Current security relies on human recognition, which is failing because AI can now clone voices with just seconds of audio, bypassing traditional identity checks.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

Live audio streams (RTP/VoIP packets), metadata (caller ID, location), and optional historical voice prints of authorized personnel.

02 • Processing & AI Core

Spectral analysis for synthetic artifacts, prosody modeling (rhythm/pitch), and cross-referencing against known speaker profiles using deep learning.

03 • Actionable Deliverables

A real-time risk score (0-100), visual alerts on the user's interface, and automated triggers for secondary authentication (MFA/Callback).

Step 5

CONSTRAINTS

  • Must operate in near real-time (latency < 200ms)
  • Privacy-preserving (GDPR/DPDP Act compliance)
  • Must handle diverse Indian accents and noisy channel conditions
  • Must be scalable for high-concurrency enterprise environments
Step 6

JURY METRICS

  • Inference latency (ms)
  • False Acceptance Rate (FAR) and False Rejection Rate (FRR)
  • Detection accuracy on unseen synthetic audio datasets
  • System uptime and API response time
Step 7

CORE BOTTLENECK

The 'Real-Time' constraint combined with 'Acoustic Artifact Analysis'—detecting subtle phase inconsistencies in compressed VoIP audio without introducing noticeable lag.

Why You Should Choose This PS (Pros)

  • High national security relevance (AICTE/Cyber Security Cell)
  • Clear, measurable success criteria
  • High potential for commercialization as a B2B SaaS product

Challenges & Risks to Watch (Cons)

  • Requires high-quality training datasets of both real and deepfake audio
  • Complex integration with existing telecom infrastructure
  • Risk of high false positives in poor network conditions
Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile
React.jsTailwind CSSLucide React
Backend & APIs
FastAPIWebSockets (for streaming)Python
AI / ML & Models
Wav2Vec 2.0 / HuBERT for feature extractionLightGBM for risk scoringPyTorch
Database & Cloud
PostgreSQLRedisMinIO

Killer Features to Impress the SIH Jury

Dynamic 'Confidence Meter' that updates as the conversation progresses
'Voice Fingerprint' vault that allows users to register their own voice for high-security verification
Explainable AI (XAI) dashboard showing exactly which acoustic feature triggered the alert
Offline-first edge inference mode for sensitive government calls
View Official SIH 2026 Portal Raw Text
▼
•Background Recent advancements in generative AI and neural speech synthesis have made high-fidelity voice cloning possible from only a few seconds of recorded audio. Threat actors are exploiting these capabilities to impersonate CXOs,government officials, and trusted individuals in order to initiate fraudulent financial transactions, manipulate employees,or bypass verification procedures in high-risk workflows. Conventional call verification methods—such as caller ID, manual call-back, and basic voice familiarity—are no longer sufficient to distinguish genuine callers from AI-generated or manipulated voices, especially in high-pressure social engineering scenarios.

These attacks are increasingly orchestrated over VoIP, mobile networks, and enterprise collaboration platforms,sometimes combined with leaked personal information to create highly convincing narratives. The absence of automated detection of synthetic or cloned voices in real time significantly increases the likelihood of large-scale financial fraud and reputational damage to institutions that rely heavily on telephonic instructions and approvals.

•Problem Statement Current telephony and communication ecosystems lack a robust, AI-driven mechanism to detect and flag voice cloning or synthetic speech impersonation during live calls. Existing solutions rarely perform granular analysis of acoustic artifacts, prosody, and speech generation patterns and typically cannot provide an actionable risk score while the conversation is ongoing.There is a need for an end-to-end security framework that can analyze incoming voice streams in near real time,determine the likelihood that the caller is using a cloned or AI-generated voice, and provide timely alerts and recommendations before sensitive actions—such as approval of fund transfers or disclosure of confidential information—are taken. The solution must be privacy-preserving, scalable across telecom and enterprise environments, and support multilingual contexts with diverse Indian accents and dialects.
•Proposed Solution Develop an AI-powered, real-time voice integrity verification framework that integrates advanced deep learning,digital signal processing, and contextual analysis to detect AI-generated or manipulated voices. The system should continuously process live or near live audio streams from telephony, VoIP, and collaboration platforms,extract discriminative features, and compute a dynamic impersonation risk score.The framework should expose APIs and SDKs for seamless integration with banking applications, enterprise communication systems, and telecom operator infrastructures, enabling proactive fraud prevention and enhanced cyber resilience in voice channels.
•Key Components
•Multi-Layer Voice Authenticity Analysis o Acoustic and spectral analysis using deep learning models to detect synthesis artifacts, phase inconsistencies, and spectral signatures indicative of cloned or AI-generated audio.

o Prosody and behavioral analysis to model speech rhythm, pitch contours, pauses, and microvariations, differentiating natural human speech from neural TTS outputs.

o Cross-session consistency checks comparing ongoing call features against historical genuine samples (where available) to detect anomalies in speaker identity.

•Real-Time Risk Scoring Engine o Continuous computation of a confidence/risk score indicating the probability of impersonation or synthetic speech.

o Threshold-based alerting logic configurable for different risk scenarios (for example, high-value transaction calls, privileged access approvals).

o Contextual enrichment using metadata such as call origin, known contact information, transaction context, and historical fraud indicators.

•Alerting and User Interaction Layer o Multi-channel alert mechanisms (UI prompts, SMS/email, in-app notifications) for frontline staff and end users.

o Pre-transaction warning prompts recommending secondary verification such as call-back, multifactor authentication, or escalation to supervisors.

o Configurable workflows for banks,enterprises, and government agencies to define automated responses when impersonation risk crosses thresholds.

•Privacy and Compliance Module o Minimal retention of voice recordings with options for on-device or edge inference to reduce central storage of sensitive audio data.

o Support for anonymization or feature-only logging to comply with data protection and privacy requirements.

•Platform and Integration APIs o REST/gRPC APIs and SDKs for integration with core banking systems, contact center platforms, enterprise communication tools, and telecom networks.

o Support for multiple Indian languages and regional accents through language-agnostic feature extraction and language-specific acoustic models.

•Expected Outcomes
•Significant reduction in financial fraud and social engineering incidents driven by voice cloning and AIenabled impersonation.
•Improved trust and assurance in voice-based communication channels for individuals, financial institutions, enterprises, and government organizations.
•Early detection of AI-driven social engineering attacks, enabling proactive containment and incident response.
•A reusable security layer for telecom operators and enterprises that strengthens overall cyber resilience and aligns with national cybersecurity objectives.