AI is changing security on both sides. It helps attackers write more convincing scams and gives them new systems to break, and it also gives defenders new tools. Build a project that uses AI to protect people or organizations, or that makes AI systems themselves harder to misuse.

You don’t need to be a security professional to compete. Some of the biggest risks are everyday ones that small businesses, nonprofits, and families deal with constantly:

• Phishing emails and texts that look like they came from a bank, vendor, or coworker
• Fake invoices and payment-change requests sent to whoever pays the bills
• Scam calls using cloned voices
• Outdated website plugins, weak passwords, and accounts nobody remembers creating
• Employees pasting customer data into public chatbots
• A small business adding an AI chatbot to its website without realizing customers can talk it into saying or doing things it shouldn’t

Projects can also go deeper: protecting an agent from prompt injection, probing a model for data leaks, or documenting what a model depends on.

Requirements:

• The project must address a specific, clearly stated security problem.
• Any offensive testing must target only systems you own or are explicitly authorized to test. Projects that attack third-party systems, or ship ready-to-use attack tooling without safeguards, are not eligible.
• Your demo must show the problem and how your project responds to it.

What a strong entry looks like:

• Clearly explains who is at risk, what could go wrong, and how the attack actually happens.
• Shows the problem happening, then shows the project catching, stopping, or explaining it.
• Is usable by the people who need it. A tool for a five-person office can’t assume an IT department.
• Is honest about its limits. Every defense has gaps, and a strong entry names its own.
• Avoids creating new problems, like a scam detector that sends private emails to a third party.

Prize: One winning team receives The AI Cybersecurity Handbook by Caroline Wong and Software Transparency by Chris Hughes and Tony Turner.