Bae System Problem Statements

Recording

PRODIGY9: Problem Statement Sharing Session

Bae Systems: Problem Statement - Untangling Threat Tactics to Drive Defence

Prize: 12-months of mentorship with 1-on-1 monthly meetings and networking with other SMEs as arranged by the mentor

1st place $450 USD - Microsoft Funded
2nd place $225 USD - Microsoft Funded

Current State: Many threat intelligence research teams publish insights on cyber threat actors’ behaviour, and their latest attack campaigns. Some teams will helpfully tag TTPs (Tactics, Techniques & Procedures) in their report in accordance with Mitre ATT&CK, the globally recognised framework and knowledge base for tracking attacker tactics and techniques, and some teams will provide security control recommendations in their reports; ATT&CK also recommends security controls to detect and mitigate against each technique. Other TI teams will publish reports without obvious alignment to ATT&CK, and the reader must trawl through reports to understand attackers’ tactics, and how to defend their organisation against them.

Problem Statement: Create a tool to identify TTPs from many recent public threat intelligence research reports (e.g. webpages, pdfs), whether tagged clearly, hidden in the text, or described in a different way, and using Mitre ATT&CK, provide the user with a clear summary of recommended security controls for detection and mitigation. A senior analyst or cyber security manager should be able to run this tool on a monthly basis, to ensure they are prioritising appropriate defences for the current threat landscape. AI methods such as a Large Language Model could help you with your solution.

Data Source: Public threat intelligence research blogs and articles; Mitre ATT&CK Framework
https://attack.mitre.org/

Report example where TTPs are tagged well:
https://thedfirreport.com/2024/04/29/from-icedid-to-dagon-locker-ransomware-in-29-days/

Report example with less obvious TTPs:
https://unit42.paloaltonetworks.com/alloy-taurus/

Tech Stack: Azure AI (Document Intelligence), Azure AI Search, Azure OpenAI

PRODIGY9: Problem Statement 2 - Create an AI service to compose a new character

Prize: 3-month internship at PRODIGY9 Co., Ltd. (Bangkok or Remote) and a special CWB edition custom designed scarf

Given a large image dataset from character making websites such as https://storior.com/ or https://picrew.me/en/ which contains images that can be composed together to make a character (for example, swords, shields, helmets for a knight).

We would like you to create an AI service such that when given a prompt, it would select the individual parts from the library of images at your disposal to compose a new character that would best match the given prompt. If no images are available or the AI believes there are not enough data/images available to satisfy the prompt, we would like for it to simply make a suggestion that will most closely match the prompt.A small set of images will be provided for testing.

Tech Stack:
– Azure AI Vision
– Azure OpenAI

Success Criteria:
– Creativity on how the prompt UI is presented.
– Quality of the generated result.
– AI usage costs per prompt

Sponsored by:

Powered by:

Stay connected: