PhantomClick

Home Page
ScamBrain - OCR & Psychographic Analysis
DNA of Phishing URL - Advanced Risk Scoring
Secure Snapshot - Isolated Website Investigation
Scam Replay - Interactive Threat Visualization
Automated Forensic Report Generation

Inspiration

PhantomClick was inspired by real scam incidents where people lost money after clicking links that looked completely legitimate like fake delivery updates, bank alerts, and KYC messages. Seeing even tech-aware users fall for these scams made us realize that generic warnings aren’t enough. We wanted to build something that shows what actually happens behind a suspicious link before any real damage is done.

What it does

PhantomClick is an AI-powered scam investigation platform that analyzes suspicious SMS messages and links. Instead of just flagging them, it safely opens links inside an isolated sandbox, observes their real behavior, detects phishing and manipulation techniques, and generates clear visual proof along with forensic-ready reports.

How we built it

We have built this project as a multi-stage pipeline. SMS screenshots are processed using OCR to extract text and links. AI models analyze intent, urgency, and impersonation patterns, while URL risk is scored using heuristic rules and machine learning. High-risk links are then opened in a secure sandbox where their actions are monitored and recorded. Finally, the system generates explainable results and structured reports.

Challenges we ran into

Safely interacting with malicious links without exposing users was our biggest challenge. Reducing false positives while maintaining strong detection accuracy also required careful tuning. Another major challenge was converting complex technical behavior into simple, understandable insights for non-technical users.

Accomplishments that we’re proud of

We’re proud of building a system that goes beyond detection and delivers real, explainable proof. Creating automated, court-ready forensic reports and scam replays that visually explain an attack was a key milestone for us as engineering students.

What we learned

We learned how modern scams combine technical exploits with psychological manipulation. The project also helped us understand the importance of explainability, user trust, and secure system design in cybersecurity tools.

What’s next for PhantomClick

Next, we plan to improve model accuracy, expand scam detection coverage, and integrate PhantomClick with banking apps, telecom SMS gateways, and cybercrime investigation workflows to stop scams earlier and at scale.