From prompt attacks to data leaks, LLMs offer new capabilities and new threats

From prompt attacks to data leaks, LLMs offer new capabilities and new threats

SPONSORED BY DOIT

On this sponsored episode, Ben and Ryan talk to Eduardo Mota, Sr. Cloud Data Architect at DoiT, about the security threats that GenAI opens up. While there’s a lot of dangers out there, it’s not all doom and gloom; they also talk about how to mitigate these threats.

Episode notes:

The broken nose in jail scam is on the rise. With AI improvements, it’ll get harder to spot.

OWASP, a non-profit dedicated to software security, tracks the top ten security risks for LLMs.

We’ve spoken with DoiT on the podcast before about LLM hallucinations.

DoiT’s sales pitch is simple: they provide technology and expertise to clients who want to use the cloud, free of charge, with the big cloud providers paying the bills.

Source: https://stackoverflow.blog/2023/12/20/from-prompt-attacks-to-data-leaks-llms-offer-new-capabilities-and-new-threats/


You might also like this video