🇸🇬 Singapore AI CTF

Join Singapore's first AI Security focused CTF featuring machine learning security challenges in 7 domains!

Register now: go.gov.sg/singaporeaictf Event website: go.gov.sg/sgaictf

Start Time: Saturday, 26th October 8am (UTC+08 Singapore Time)

End Time: Monday, 28th October 8am (UTC+08 Singapore Time)

The categories of the AI CTF Competition are:

1) Data Analysis Participants need to utilise various data analysis and visualisation tools to extract hidden information within a given dataset.

2) Model Extraction Participants use malicious means to extract information from the model (e.g. parameters, architecture, or training data)

3) Model Fingerprinting Participants must verify watermarks and/or fingerprints in AI models to verify their authenticity and detect unauthorised copies.

4) Prompt Injection An attack where hackers use a specially crafted input to trick AI into disclosing a hidden secret.

5) Adversarial AI Image An attacker injects malicious data into the training set causing AI to misclassify an image.

6) Adversarial Audio Generation Involves replicating voices and audio using AI.

7) Model Inversion An attacker aims to infer/reconstruct input data based on model outputs.