Aggregator

Adversarial Prompting: Tutorial and Lab(link is external)

Embrace The Red
1 year 10 months ago
To learn more about Prompt Engineering and Prompt Injections I put together this tutorial + lab for myself. It is as a Jupyter Notebook to experiement and play around with this novel attack technique, learn and experiment. The examples reach from simple prompt engineering scenarios, such as changing the output message to a specific text, to more complex adversarial prompt challenges such as JSON object injection, HTML injection/XSS, overwriting mail recipients or orders of an OrderBot and also data exfiltration.

Episode 004 - Jeremy MountainJohnson

The Blue Team Diaries
1 year 10 months ago

As the threat landscape continues to evolve, the integration of automation into network security has become an increasingly critical need for organizations to improve the performance of their security tools. 

Join host Peter Manev and guest Jeremy MountainJohnson, a Security Analyst serving on the board for the Minnesota Chapter of High Technology Crime Investigation Association, as they explore the latest advancements in cybersecurity automation and discuss the areas for improvements.

Find Jeremy: 
Linkedin: https://www.linkedin.com/in/mountainjohnson/


Video: Prompt Injections - An Introduction(link is external)

Embrace The Red
1 year 10 months ago
There are many prompt engineering classes and currently pretty much all examples are vulnerable to Prompt Injections. Especially Indirect Prompt Injections are dangerous as we discussed before. Indirect Prompt Injections allow untrusted data to take control of the LLM (large language model) and give an AI a new instructions, mission and objective. Bypassing Input Validation Attack payloads are natural language. This means there are lots of creative ways an adversary can inject malicious data that bypass input filters and web application firewalls.

Managed ad