@ericyocam6Shipped: AI Voice Vishing Simulation — Real-Time Social Engineering
An open-source, AI-powered voice phishing (vishing) simulation designed to demonstrate how generative AI can enable realistic, adaptive social engineering attacks and how organizations can train employees to recognize them.
The proof of concept combines Google's Gemini 2.5 Flash for contextual conversation, ElevenLabs for realistic voice synthesis, and browser-based speech recognition to create interactive voice conversations. The AI maintains a simulated IT support persona, adapting its responses to demonstrate urgency, authority impersonation, and psychological manipulation techniques commonly associated with social engineering.
Built in Google Colab, the system integrates real-time speech-to-text, LLM reasoning, text-to-speech generation, and timestamped conversation logging through Google Drive. Its interactive interface supports audio playback and transcript review for security awareness training.
The project demonstrates how AI lowers the barriers to sophisticated voice phishing while providing educators, cybersecurity professionals, and researchers with a controlled environment for studying and defending against AI-enabled social engineering. Intended exclusively for authorized training and academic research.
Comments2
Replaying the audio and transcript after a fake IT support call shows an employee the exact moment they caved.
Thanks, Ryan. Exactly. One of the key benefits of the simulation is the ability to review the audio and transcript afterward, helping employees recognize where urgency, authority impersonation, or other social engineering tactics influenced their decisions. The goal isn't simply to demonstrate how convincing AI-generated voices can be, but to turn those interactions into practical learning opportunities. I see real potential for this approach in cybersecurity awareness training, particularly as AI-enabled voice phishing becomes more sophisticated. Appreciate the feedback!
2 comments
Replaying the audio and transcript after a fake IT support call shows an employee the exact moment they caved.
Thanks, Ryan. Exactly. One of the key benefits of the simulation is the ability to review the audio and transcript afterward, helping employees recognize where urgency, authority impersonation, or other social engineering tactics influenced their decisions. The goal isn't simply to demonstrate how convincing AI-generated voices can be, but to turn those interactions into practical learning opportunities. I see real potential for this approach in cybersecurity awareness training, particularly as AI-enabled voice phishing becomes more sophisticated. Appreciate the feedback!