AfriVish-Bench

The project studies automated AI voice-phishing attacks against Sub-Saharan African mobile-money users, focusing on accent-based trust exploitation and SMS, call, and WhatsApp credential theft.

Endorsed by

Mark

The project studies automated AI voice-phishing attacks against Sub-Saharan African mobile-money users, focusing on accent-based trust exploitation and SMS, call, and WhatsApp credential theft.

Endorsed by

Mark

Project Details

The project addresses a critical gap in cybersecurity: the rapid escalation of fully automated AI voice phishing (vishing) attacks targeting mobile users in Sub-Saharan Africa. Existing anti-spoofing benchmarks evaluate synthetic voice detection in a vacuum, entirely missing the real-world context of how these multi-channel attacks operate against African financial systems like EcoCash, MTN MoMo, and M-Pesa.

The New Attack Vector: Real-Time AI Agents Historically, vishing required trained human callers, making it expensive and hard to scale. The new attack vector changes this completely:

Fully Automated & Scalable: Cybercriminals can now buy end-to-end platforms (like ATHR) that use generative AI voice agents to conduct live, autonomous social engineering calls. A single operator can target hundreds of people simultaneously without ever speaking.

Real-Time Adaptation: Unlike old, pre-recorded robocalls that failed if you asked an unexpected question, these AI agents synthesize responses in real-time with very low latency. They adapt seamlessly, making the call feel like a completely normal conversation.

The "Accent Trust" Exploit in Africa The project highlights a specific social engineering tactic that is uniquely effective in African markets:

Implicit Corporate Legitimacy: In many African countries, a clean American or British English accent carries a strong association with institutional authority and corporate legitimacy.

Bypassing Natural Skepticism: While a mobile user might be highly suspicious of a local accent asking for sensitive account details, an AI-synthesized foreign accent bypasses these natural defenses. The victim is much more likely to trust the caller.

Low AI Literacy: General populations in the region have limited exposure to the realities of modern AI voice cloning, meaning they are less equipped to recognize synthetic audio.

How the Attack Operates The project outlines a specific multi-channel attack flow designed to drain mobile wallets:

The Lure: The victim receives a spoofed email or SMS (e.g., "Your account has been locked") containing a callback number.

The AI Agent Call: When the victim calls the number, an AI agent takes over. Using a trusted foreign accent and a sophisticated script, the AI explains a fake security issue or account update.

The WhatsApp Handoff: Because WhatsApp is the primary communication channel in the region, the AI will often redirect the victim to add a specific WhatsApp number to continue "secure support."

Credential Theft: The AI manipulates the victim into handing over a One-Time Password (OTP) or PIN. The automated system then instantly uses these credentials to drain the victim's mobile money account.

Hackathon paper: AfriVish-Bench

Theory of Impact

Sub-Saharan Africa’s reliance on mobile money, such as EcoCash, tied to WhatsApp communications creates a critically underprotected attack surface. Because foreign accents carry implicit corporate legitimacy in the region, automated AI voice agents easily bypass natural user skepticism to harvest OTPs. Currently, no anti-spoofing benchmark addresses this intersection of AI-synthesized agents and multi-channel African mobile fraud.
By developing AfriVish-Bench, we provide the first empirical measurement of defense capabilities against industrial-scale vishing in low-resource environments. Our work directly tests the coverage gap of current watermark systems like SynthID. Deploying our proposed meta-learner ensemble as a live API will allow local financial institutions to actively detect acoustic liveness and social engineering intent. This neutralizes the "accent trust" exploit and protects vulnerable populations from scalable mobile wallet theft.

People

Tinevimb Musingadi

Team Member

Track Record

Global South AIS Hackathon (Apart Research), 2026

Grants Received– no grants recorded

Add grant

Funding Asks

Funding ask

Open

Minimum

$15,000

Ideal

$46,000

What this ask is

I will translate AfriVish-Bench from a static evaluation framework into a deployable real-time safety layer that intercepts multi-channel TOAD (Telephone-Oriented Attack Delivery) campaigns. The recent commercialization of end-to-end vishing infrastructure like ATHR enables autonomous AI agents to adaptively extract OTPs in real-time, targeting mobile money systems like EcoCash and M-Pesa. To counter this, the funding will first resource our fundamental research: synthesizing a 1,300-sample audio dataset grounded in African fraud archetypes and evaluating baselines like the VGGish-LSTM hybrid and Google SynthID watermark detection.
Once the detection metrics—including AUC-ROC, EER, and LLM-as-judge transcripts—are validated, the project will scale from research into an active defense mechanism. I will prototype the API using Python and Google AI Studio to handle real-time inference, and host the highly scalable backend on Render. We will also construct a live adversarial test harness, routing an LLM-driven generative agent through VOIP to simulate low-latency attacks, to rigorously red-team the API under operationally realistic conditions. Ultimately, this transforms AfriVish-Bench into a compliance-ready detection tool that regional telecoms can integrate to stop automated fraud before the WhatsApp handoff.

How the money will be spent

Dataset Generation & Curation: Acquiring localized authentic audio and purchasing API credits for Google Cloud TTS and ElevenLabs. This will be used to programmatically generate 1,300 synthetic samples across six regional scam archetypes.
Infrastructure & Deployment: Enterprise-tier cloud compute is needed for training the VGGish-LSTM acoustic models. This budget will also cover hosting the production-ready detection API on Render.
Adversarial Harness & Red-Teaming: Funding VOIP and WhatsApp routing infrastructure is required. This budget will also cover low-latency LLM inference, utilizing models like Gemini 2.0 Flash, to build the live real-time voice agent test pipeline.
Developer Stipends & Research Compliance: Compensating dedicated time to build the safety layer architecture using Python. Funding will also ensure all outputs align with the Zimbabwe Cyber and Data Protection Act and POPIA.

Discussion

Private comments in this thread are only shown to approved funders and grant reviewers. Email hi@grantmaking.ai or to request access.

Private UserPrivate15d?

Mark GaffleyJudge · Global South AIS HackathonEndorsement15d

The project can be commended for identifying a real and significant threat and providing sufficient evidence to highlight the magnitude of the threat. I appreciated the explanation for the African context and the bullets describing the ways in which these attacks may take advantage of African citizens. The research gap was clear and the challenge / solution for it also well thought out. 2.3. highlighted a novel form of an existing challenge enabled by AI technologies. The author is also well aware of the limits to their plan to address the challenge and presents what appear to be workable solutions. I say this because I do not have the technical competence to adequately assess whether they are indeed workable. Throughout the author also referenced existing evidence highlighting that the question had been well considered. I was also impressed by the ethical safeguard considerations and the consideration of applicable legislation in Zimbabwe and RSA. The balance between technical detail and explainability was also thoughtfully considered, making it a well executed project.