Hacktoberfest Hack Day Kolkata x OWASP JIS University

Build an original project that uses open-source or open-weight AI as an important part of how it works. Teams could create an agent skill, build with an open-weight large or small language model, or build or adapt an open-source model harness.

Build an original project that uses artificial intelligence to address a real and clearly defined cybersecurity problem. The AI component should contribute substantively to the security functionality, rather than being included only as a superficial feature. Teams could build a threat detection system, a vulnerability analysis tool, a security awareness assistant, or an AI-powered defensive security solution. These are examples within one challenge, and teams may combine them.

The project must address a clearly defined cybersecurity problem.

The project must be published in a public GitHub repository and use an open-source license.

The AI component must have a meaningful and demonstrable role in the security functionality of the project.

The project must follow responsible security practices throughout development and demonstration.

Teams should be prepared to explain the relationship between the AI component and the security functionality, identify the attack or threat being addressed, and describe how their solution detects, prevents, or mitigates it.

Build an original project that uses Snowflake CoCo alongside a freely accessible dataset to create a meaningful open-source AI application. The Snowflake and AI components should both contribute substantively to the project’s functionality, rather than being included only as superficial features. Teams could build a data-driven AI application, an intelligent analytics dashboard, a natural language query tool, or an AI-powered data pipeline. These are examples within one challenge, and teams may combine them.

The project must use Snowflake CoCo to find, understand, or work with a freely accessible dataset from the Snowflake Marketplace or Snowflake sample data.

The project must be published in a public GitHub repository and use an open-source license.

The AI component must use open-source or open-weight AI as a meaningful part of the project.

Eligible projects must combine all three elements: Snowflake CoCo, a freely accessible Snowflake dataset, and open-source or open-weight AI.

Teams should be prepared to show how CoCo helped them explore the data or build the project, identify the dataset used and where it came from, and demonstrate the AI component’s role in the final solution.

It’s time to see how much you can build with a lightweight, open model. Gemma 4 packs multimodal intelligence into an open-weights model that you can access through the Gemini API. So, what can Gemma 4 bring to your project?

• Multimodal Experience: Work with text and images to create an assistant that understands more of what users share.
• Focused AI Tools: Build a focused AI tool for learning, creativity, productivity, or your community.
• Rapid Prototyping: Experiment with an open model while using the Gemini API to move quickly from an idea to a working prototype.

Bring your idea to life… what will you build with Gemma 4 today?